<x:xmpmeta tsc:version="2.0.1" xmlns:x="adobe:ns:meta/" xmlns:tsc="http://www.techsmith.com/xmp/tsc/">
   <rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:xmp="http://ns.adobe.com/xap/1.0/" xmlns:xmpDM="http://ns.adobe.com/xmp/1.0/DynamicMedia/" xmlns:xmpG="http://ns.adobe.com/xap/1.0/g/" xmlns:xmpMM="http://ns.adobe.com/xap/1.0/mm/" xmlns:tscDM="http://www.techsmith.com/xmp/tscDM/" xmlns:tscIQ="http://www.techsmith.com/xmp/tscIQ/" xmlns:tscHS="http://www.techsmith.com/xmp/tscHS/" xmlns:stDim="http://ns.adobe.com/xap/1.0/sType/Dimensions#" xmlns:stFnt="http://ns.adobe.com/xap/1.0/sType/Font#" xmlns:exif="http://ns.adobe.com/exif/1.0" xmlns:dc="http://purl.org/dc/elements/1.1/">
      <rdf:Description dc:date="2017-11-16 12:00:17 PM" dc:source="Camtasia,9.1.0,enu" dc:title="k_37tsa1" tscDM:firstFrame="k_37tsa1_First_Frame.png" tscDM:originId="693765A9-5AAD-46AF-9EF3-544354460A8D" tscDM:project="k_37tsa1.tscproj">
         <xmpDM:duration xmpDM:scale="1/1000" xmpDM:value="4367233"/>
         <xmpDM:videoFrameSize stDim:unit="pixel" stDim:h="1080" stDim:w="1440"/>
         <tsc:langName>
            <rdf:Bag>
               <rdf:li xml:lang="en-US">English</rdf:li></rdf:Bag>
         </tsc:langName>
         <xmpDM:Tracks>
            <rdf:Bag>
               <rdf:li>
                  <rdf:Description xmpDM:trackType="ScreenText" xmpDM:frameRate="f1000" xmpDM:trackName="Screen Text">
                     <xmpDM:markers>
                        <rdf:Seq>
                           <rdf:li><rdf:Description xmpDM:name="Overview What is a time series? Autoregressive Models Moving Average Models Integrated Models ARMA, ARIMA, SARIMA, FARIMA models Note: These" xmpDM:startTime="2100" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="slides are based on R." xmpDM:startTime="2100" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Jain, “The Art of Computer Systems Performance Analysis,” 2nd Edition (in preparation)." xmpDM:startTime="2100" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="2100" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Stochastic Processes Ordered sequence of random observations Example: Number of virtual machines in a server Number of page faults Number" xmpDM:startTime="20233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="of queries over time Analysis Technique: Time Series Analysis Long-range dependence and self-similarity in such processes can invalidate many previous" xmpDM:startTime="20233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="results" xmpDM:startTime="20233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Stochastic Processes: Key Questions What is a time series? What are different types of time series models? How to fit" xmpDM:startTime="78967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="a model to a series of measured data? What is a stationary time series? Is it possible to model a" xmpDM:startTime="78967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="series that is not stationary? How to model a series that has a periodic or seasonal behavior as is common" xmpDM:startTime="78967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="in video streaming?" xmpDM:startTime="78967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Stochastic Processes : Key Questions (Cont) What are heavy-tailed distributions and why they are important? How to check if a" xmpDM:startTime="125700" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="sample of observations has a heavy tail? What are self-similar processes? What are short-range and long-range dependent processes? Why long-range" xmpDM:startTime="125700" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="dependence invalidates many conclusions based on previous statistical methods? How to check if a sample has a long-range dependence?" xmpDM:startTime="125700" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="What is a Time Series Time series = Stochastic Process A sequence of observations over time." xmpDM:startTime="179067" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Examples: Price of a stock over successive days Sizes of video frames Sizes of packets over network Sizes of queries" xmpDM:startTime="179067" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="to a database system Number of active virtual machines in a cloud Goal: Develop models of such series for resource" xmpDM:startTime="179067" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="allocation and improving user experience." xmpDM:startTime="179067" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Time t xt" xmpDM:startTime="179067" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Autoregressive Models Predict the variable as a linear regression of the immediate past value: Here, is the best estimate of" xmpDM:startTime="216333" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="xt given the past history Even though we know the complete past history, we assume that xt can be predicted" xmpDM:startTime="216333" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="based on just xt-1." xmpDM:startTime="216333" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Auto-Regressive = Regression on Self Error: Model: Best a0 and a1  minimize the sum of square of errors TP_tmp" xmpDM:startTime="216333" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="TP_tmp TP_tmp TP_tmp TP_tmp" xmpDM:startTime="216333" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.1" xmpDM:startTime="345000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="The number of disk access for 50 database queries were measured to be: 73, 67, 83, 53, 78, 88, 57," xmpDM:startTime="345000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="1, 29, 14, 80, 77, 19, 14, 41, 55, 74, 98, 84, 88, 78, 15, 66, 99, 80, 75, 124," xmpDM:startTime="345000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="103, 57, 49, 70, 112, 107, 123, 79, 92, 89, 116, 71, 68, 59, 84, 39, 33, 71, 83, 77," xmpDM:startTime="345000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="37, 27, 30." xmpDM:startTime="345000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="For this data: TP_tmp TP_tmp TP_tmp" xmpDM:startTime="345000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Autoregressive Models Predict the variable as a linear regression of the immediate past value: Here, is the best estimate of" xmpDM:startTime="360733" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="xt given the past history Even though we know the complete past history, we assume that xt can be predicted" xmpDM:startTime="360733" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="based on just xt-1." xmpDM:startTime="360733" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Auto-Regressive = Regression on Self Error: Model: Best a0 and a1  minimize the sum of square of errors TP_tmp" xmpDM:startTime="360733" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="TP_tmp TP_tmp TP_tmp TP_tmp" xmpDM:startTime="360733" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.1" xmpDM:startTime="365300" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="The number of disk access for 50 database queries were measured to be: 73, 67, 83, 53, 78, 88, 57," xmpDM:startTime="365300" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="1, 29, 14, 80, 77, 19, 14, 41, 55, 74, 98, 84, 88, 78, 15, 66, 99, 80, 75, 124," xmpDM:startTime="365300" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="103, 57, 49, 70, 112, 107, 123, 79, 92, 89, 116, 71, 68, 59, 84, 39, 33, 71, 83, 77," xmpDM:startTime="365300" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="37, 27, 30." xmpDM:startTime="365300" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="For this data: TP_tmp TP_tmp TP_tmp" xmpDM:startTime="365300" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.1" xmpDM:startTime="436867" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="(Cont) The AR(1) model for the series is: The predicted value of x2 given x1 is: The actual observed value" xmpDM:startTime="436867" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="of is 67." xmpDM:startTime="436867" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Therefore, the prediction error is: Sum of squared errors SSE = 32995.57" xmpDM:startTime="436867" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="TP_tmp TP_tmp TP_tmp TP_tmp" xmpDM:startTime="436867" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.1" xmpDM:startTime="483300" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="The number of disk access for 50 database queries were measured to be: 73, 67, 83, 53, 78, 88, 57," xmpDM:startTime="483300" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="1, 29, 14, 80, 77, 19, 14, 41, 55, 74, 98, 84, 88, 78, 15, 66, 99, 80, 75, 124," xmpDM:startTime="483300" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="103, 57, 49, 70, 112, 107, 123, 79, 92, 89, 116, 71, 68, 59, 84, 39, 33, 71, 83, 77," xmpDM:startTime="483300" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="37, 27, 30." xmpDM:startTime="483300" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="For this data: TP_tmp TP_tmp TP_tmp" xmpDM:startTime="483300" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.1" xmpDM:startTime="487500" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="(Cont) The AR(1) model for the series is: The predicted value of x2 given x1 is: The actual observed value" xmpDM:startTime="487500" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="of is 67." xmpDM:startTime="487500" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Therefore, the prediction error is: Sum of squared errors SSE = 32995.57" xmpDM:startTime="487500" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="TP_tmp TP_tmp TP_tmp TP_tmp" xmpDM:startTime="487500" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.1" xmpDM:startTime="495567" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="The number of disk access for 50 database queries were measured to be: 73, 67, 83, 53, 78, 88, 57," xmpDM:startTime="495567" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="1, 29, 14, 80, 77, 19, 14, 41, 55, 74, 98, 84, 88, 78, 15, 66, 99, 80, 75, 124," xmpDM:startTime="495567" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="103, 57, 49, 70, 112, 107, 123, 79, 92, 89, 116, 71, 68, 59, 84, 39, 33, 71, 83, 77," xmpDM:startTime="495567" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="37, 27, 30." xmpDM:startTime="495567" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="For this data: TP_tmp TP_tmp TP_tmp" xmpDM:startTime="495567" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.1" xmpDM:startTime="499333" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="(Cont) The AR(1) model for the series is: The predicted value of x2 given x1 is: The actual observed value" xmpDM:startTime="499333" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="of is 67." xmpDM:startTime="499333" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Therefore, the prediction error is: Sum of squared errors SSE = 32995.57" xmpDM:startTime="499333" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="TP_tmp TP_tmp TP_tmp TP_tmp" xmpDM:startTime="499333" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.1" xmpDM:startTime="532800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Fit an AR(1) model to the following sample of 50 observations: 83, 86, 46, 34, 130, 109, 100, 81, 84," xmpDM:startTime="532800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="148, 93, 76, 69, 40, 50, 56, 63, 104, 35, 55, 124, 52, 55, 81, 33, 76, 83, 90, 94," xmpDM:startTime="532800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="37, -2, 33, 105, 133, 78, 50, 115, 149, 98, 110, 25, 82, 59, 80, 43, 58, 88, 78, 55," xmpDM:startTime="532800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="68." xmpDM:startTime="532800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Find a0, a1 and the minimum SSE." xmpDM:startTime="532800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="532800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.1" xmpDM:startTime="549567" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="(Cont) The AR(1) model for the series is: The predicted value of x2 given x1 is: The actual observed value" xmpDM:startTime="549567" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="of is 67." xmpDM:startTime="549567" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Therefore, the prediction error is: Sum of squared errors SSE = 32995.57" xmpDM:startTime="549567" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="TP_tmp TP_tmp TP_tmp TP_tmp" xmpDM:startTime="549567" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.1" xmpDM:startTime="550133" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="The number of disk access for 50 database queries were measured to be: 73, 67, 83, 53, 78, 88, 57," xmpDM:startTime="550133" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="1, 29, 14, 80, 77, 19, 14, 41, 55, 74, 98, 84, 88, 78, 15, 66, 99, 80, 75, 124," xmpDM:startTime="550133" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="103, 57, 49, 70, 112, 107, 123, 79, 92, 89, 116, 71, 68, 59, 84, 39, 33, 71, 83, 77," xmpDM:startTime="550133" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="37, 27, 30." xmpDM:startTime="550133" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="For this data: TP_tmp TP_tmp TP_tmp" xmpDM:startTime="550133" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.1" xmpDM:startTime="585167" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="(Cont) The AR(1) model for the series is: The predicted value of x2 given x1 is: The actual observed value" xmpDM:startTime="585167" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="of is 67." xmpDM:startTime="585167" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Therefore, the prediction error is: Sum of squared errors SSE = 32995.57" xmpDM:startTime="585167" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="TP_tmp TP_tmp TP_tmp TP_tmp" xmpDM:startTime="585167" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.1" xmpDM:startTime="587167" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Fit an AR(1) model to the following sample of 50 observations: 83, 86, 46, 34, 130, 109, 100, 81, 84," xmpDM:startTime="587167" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="148, 93, 76, 69, 40, 50, 56, 63, 104, 35, 55, 124, 52, 55, 81, 33, 76, 83, 90, 94," xmpDM:startTime="587167" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="37, -2, 33, 105, 133, 78, 50, 115, 149, 98, 110, 25, 82, 59, 80, 43, 58, 88, 78, 55," xmpDM:startTime="587167" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="68." xmpDM:startTime="587167" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Find a0, a1 and the minimum SSE." xmpDM:startTime="587167" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="587167" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Stationary Process Each realization of a random process will be different: x is function of the realization i (space) and" xmpDM:startTime="591433" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="time t: x(i, t) We can study the distribution of xt in space." xmpDM:startTime="591433" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Each xt has a distribution, e.g.," xmpDM:startTime="591433" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Normal If this same distribution (normal) with the same parameters ¹, ¾ applies to xt+1, xt+2, …, we say xt" xmpDM:startTime="591433" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="is stationary." xmpDM:startTime="591433" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="xt t TP_tmp" xmpDM:startTime="591433" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Stationary Process (Cont) Stationary = Standing in time  Distribution does not change with time." xmpDM:startTime="868033" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Similarly, the joint distribution of xt and xt-k depends only on k not on t." xmpDM:startTime="868033" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="The joint distribution of xt, xt-1, …, xt-k depends only on k not on t." xmpDM:startTime="868033" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="868033" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Autocorrelation Covariance of xt and xt-k = Auto-covariance at lag k For a stationary series: Statistical characteristics do not depend" xmpDM:startTime="913200" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="upon time t." xmpDM:startTime="913200" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Autocovariance depends only on lag k and not on time t Autocorrelation is dimensionless and is easier to interpret than" xmpDM:startTime="913200" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="autocovariance." xmpDM:startTime="913200" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="TP_tmp TP_tmp" xmpDM:startTime="913200" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.2" xmpDM:startTime="1022767" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="For the data of Example 37.1," xmpDM:startTime="1022767" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="the variance and covariance's at lag 1 and 2 are computed as follows:" xmpDM:startTime="1022767" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.2" xmpDM:startTime="1053300" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="(Cont) Small Sample  and are slightly different." xmpDM:startTime="1053300" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Not so for large samples." xmpDM:startTime="1053300" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Divisor is 48 since we used sample mean calculated from the same sample" xmpDM:startTime="1053300" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.2" xmpDM:startTime="1192933" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="(Cont) Note: Only 48 pairs of {xt, xt-1}  Divisor is 47" xmpDM:startTime="1192933" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.2" xmpDM:startTime="1267400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="(Cont) Small Sample  and are slightly different." xmpDM:startTime="1267400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Not so for large samples." xmpDM:startTime="1267400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Divisor is 48 since we used sample mean calculated from the same sample" xmpDM:startTime="1267400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.2" xmpDM:startTime="1272933" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="(Cont) Note: Only 48 pairs of {xt, xt-1}  Divisor is 47" xmpDM:startTime="1272933" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.2" xmpDM:startTime="1283267" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="(Cont) Lag k Autocorrelation rk 0 1 2 1.0" xmpDM:startTime="1283267" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="1283267" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="White Noise Errors et are normal independent and identically distributed (IID) with zero mean and variance ¾2 Such IID sequences" xmpDM:startTime="1328000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="are called “white noise” sequences." xmpDM:startTime="1328000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Properties: TP_tmp k 0" xmpDM:startTime="1328000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="White Noise (Cont) The autocorrelation function of a white noise sequence is a spike (± function) at k=0." xmpDM:startTime="1370833" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="The Laplace transform of a ± function is a constant." xmpDM:startTime="1370833" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="So in frequency domain white noise has a flat frequency spectrum." xmpDM:startTime="1370833" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="It was incorrectly assumed that white light has no color and, therefore, has a flat frequency spectrum and so random" xmpDM:startTime="1370833" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="noise with flat frequency spectrum was called white noise." xmpDM:startTime="1370833" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="t 0 f 0 Ref: http://en.wikipedia.org/wiki/Colors_of_noise" xmpDM:startTime="1370833" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="1370833" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="White Noise Errors et are normal independent and identically distributed (IID) with zero mean and variance ¾2 Such IID sequences" xmpDM:startTime="1377500" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="are called “white noise” sequences." xmpDM:startTime="1377500" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Properties: TP_tmp k 0" xmpDM:startTime="1377500" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="White Noise (Cont) The autocorrelation function of a white noise sequence is a spike (± function) at k=0." xmpDM:startTime="1426367" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="The Laplace transform of a ± function is a constant." xmpDM:startTime="1426367" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="So in frequency domain white noise has a flat frequency spectrum." xmpDM:startTime="1426367" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="It was incorrectly assumed that white light has no color and, therefore, has a flat frequency spectrum and so random" xmpDM:startTime="1426367" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="noise with flat frequency spectrum was called white noise." xmpDM:startTime="1426367" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="t 0 f 0 Ref: http://en.wikipedia.org/wiki/Colors_of_noise" xmpDM:startTime="1426367" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="1426367" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="White Noise Autocorrelations It can be shown that autocorrelations for white noise are normally distributed with mean: and variance: Therefore," xmpDM:startTime="1543433" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="their 95% confidence interval is This is generally approximated as This confidence interval can be used to check if a" xmpDM:startTime="1543433" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="particular autocorrelation is zero." xmpDM:startTime="1543433" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="TP_tmp TP_tmp TP_tmp TP_tmp" xmpDM:startTime="1543433" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.3" xmpDM:startTime="1668700" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="For the data of Example 37.1:" xmpDM:startTime="1668700" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="n=50 TP_tmp r2 is not significantly different from zero." xmpDM:startTime="1668700" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="1668700" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.2" xmpDM:startTime="1833667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Determine autocorrelations at lag 0 through 2 for the data of Exercise 37.1" xmpDM:startTime="1833667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="and determine which of these autocorrelations are significant at 95% confidence." xmpDM:startTime="1833667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="1833667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Assumptions for AR(1) Models xt is a Stationary process Linear relationship between successive values Normal Independent identically distributed errors: Normal" xmpDM:startTime="1845900" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="errors Independent errors Additive errors" xmpDM:startTime="1845900" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Visual Tests for AR(1) Models Plot xt as a function of t and look for trends xt vs." xmpDM:startTime="1950500" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="xt-1 for linearity Errors et vs." xmpDM:startTime="1950500" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="predicted values for additivity Q-Q Plot of errors for Normality Errors et vs." xmpDM:startTime="1950500" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="t for IID TP_tmp 1." xmpDM:startTime="1950500" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Plot of xt" xmpDM:startTime="1950500" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Visual Tests (Cont) 2." xmpDM:startTime="1994033" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Plot of xt vs." xmpDM:startTime="1994033" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="xt-1 xt-1 xt" xmpDM:startTime="1994033" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Visual Tests (Cont) et TP_tmp e z -80 -60 -40 -20 0 20 40 60 80 -3 -2 -1 0" xmpDM:startTime="2015767" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="1 2 3 et t 3." xmpDM:startTime="2015767" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Errors et vs." xmpDM:startTime="2015767" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="predicted values 4." xmpDM:startTime="2015767" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Q-Q Plot of errors 5." xmpDM:startTime="2015767" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Errors et vs." xmpDM:startTime="2015767" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="t" xmpDM:startTime="2015767" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.3" xmpDM:startTime="2071133" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Conduct visual tests to verify whether or not the AR(1) model fitted in Exercise 37.1" xmpDM:startTime="2071133" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="is appropriate ." xmpDM:startTime="2071133" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="2071133" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Model xt is a function of the last p values: AR(2): AR(3): TP_tmp TP_tmp TP_tmp" xmpDM:startTime="2074400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Similarly, Or Using this notation, AR(p) model is: Here, Áp is a polynomial of degree p." xmpDM:startTime="2157600" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="TP_tmp Backward Shift Operator TP_tmp TP_tmp TP_tmp TP_tmp TP_tmp" xmpDM:startTime="2157600" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation The coefficients ai's can be estimated by minimizing SSE using Multiple Linear Regression." xmpDM:startTime="2290833" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Optimal a0, a1, and a2  Minimize SSE Set the first differential to zero: TP_tmp TP_tmp TP_tmp" xmpDM:startTime="2290833" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation (Cont) The equations can be written as: Note: All sums are for t=3 to n." xmpDM:startTime="2312567" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="n-2 terms." xmpDM:startTime="2312567" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Multiplying by the inverse of the first matrix, we get: TP_tmp TP_tmp" xmpDM:startTime="2312567" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation (Cont) All sums are from t=p to t=n and have n-p terms." xmpDM:startTime="2331133" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="For larger data sets: rk is the autocorrelation at lag k (i,j)th term = r|i-j|" xmpDM:startTime="2331133" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation (Cont) The equations can be written as: Note: All sums are for t=3 to n." xmpDM:startTime="2415033" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="n-2 terms." xmpDM:startTime="2415033" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Multiplying by the inverse of the first matrix, we get: TP_tmp TP_tmp" xmpDM:startTime="2415033" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation The coefficients ai's can be estimated by minimizing SSE using Multiple Linear Regression." xmpDM:startTime="2415767" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Optimal a0, a1, and a2  Minimize SSE Set the first differential to zero: TP_tmp TP_tmp TP_tmp" xmpDM:startTime="2415767" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Similarly, Or Using this notation, AR(p) model is: Here, Áp is a polynomial of degree p." xmpDM:startTime="2416533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="TP_tmp Backward Shift Operator TP_tmp TP_tmp TP_tmp TP_tmp TP_tmp" xmpDM:startTime="2416533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Model xt is a function of the last p values: AR(2): AR(3): TP_tmp TP_tmp TP_tmp" xmpDM:startTime="2419300" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Similarly, Or Using this notation, AR(p) model is: Here, Áp is a polynomial of degree p." xmpDM:startTime="2451667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="TP_tmp Backward Shift Operator TP_tmp TP_tmp TP_tmp TP_tmp TP_tmp" xmpDM:startTime="2451667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation The coefficients ai's can be estimated by minimizing SSE using Multiple Linear Regression." xmpDM:startTime="2451933" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Optimal a0, a1, and a2  Minimize SSE Set the first differential to zero: TP_tmp TP_tmp TP_tmp" xmpDM:startTime="2451933" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation (Cont) The equations can be written as: Note: All sums are for t=3 to n." xmpDM:startTime="2452767" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="n-2 terms." xmpDM:startTime="2452767" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Multiplying by the inverse of the first matrix, we get: TP_tmp TP_tmp" xmpDM:startTime="2452767" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation (Cont) All sums are from t=p to t=n and have n-p terms." xmpDM:startTime="2453333" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="For larger data sets: rk is the autocorrelation at lag k (i,j)th term = r|i-j|" xmpDM:startTime="2453333" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.5" xmpDM:startTime="2481800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Consider the data of Example 37.1" xmpDM:startTime="2481800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="and fit an AR(2) model: SSE= 31979.39" xmpDM:startTime="2481800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Small sample  Values of a0, a1, and a2 are approximate." xmpDM:startTime="2481800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exact model by regression: SSE=31969.99" xmpDM:startTime="2481800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="2481800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation (Cont) All sums are from t=p to t=n and have n-p terms." xmpDM:startTime="2557333" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="For larger data sets: rk is the autocorrelation at lag k (i,j)th term = r|i-j|" xmpDM:startTime="2557333" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.5" xmpDM:startTime="2579533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Consider the data of Example 37.1" xmpDM:startTime="2579533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="and fit an AR(2) model: SSE= 31979.39" xmpDM:startTime="2579533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Small sample  Values of a0, a1, and a2 are approximate." xmpDM:startTime="2579533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exact model by regression: SSE=31969.99" xmpDM:startTime="2579533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="2579533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation (Cont) All sums are from t=p to t=n and have n-p terms." xmpDM:startTime="2588667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="For larger data sets: rk is the autocorrelation at lag k (i,j)th term = r|i-j|" xmpDM:startTime="2588667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation (Cont) The equations can be written as: Note: All sums are for t=3 to n." xmpDM:startTime="2588900" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="n-2 terms." xmpDM:startTime="2588900" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Multiplying by the inverse of the first matrix, we get: TP_tmp TP_tmp" xmpDM:startTime="2588900" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation The coefficients ai's can be estimated by minimizing SSE using Multiple Linear Regression." xmpDM:startTime="2592867" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Optimal a0, a1, and a2  Minimize SSE Set the first differential to zero: TP_tmp TP_tmp TP_tmp" xmpDM:startTime="2592867" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation (Cont) The equations can be written as: Note: All sums are for t=3 to n." xmpDM:startTime="2594467" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="n-2 terms." xmpDM:startTime="2594467" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Multiplying by the inverse of the first matrix, we get: TP_tmp TP_tmp" xmpDM:startTime="2594467" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation (Cont) All sums are from t=p to t=n and have n-p terms." xmpDM:startTime="2594900" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="For larger data sets: rk is the autocorrelation at lag k (i,j)th term = r|i-j|" xmpDM:startTime="2594900" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.5" xmpDM:startTime="2595333" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Consider the data of Example 37.1" xmpDM:startTime="2595333" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="and fit an AR(2) model: SSE= 31979.39" xmpDM:startTime="2595333" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Small sample  Values of a0, a1, and a2 are approximate." xmpDM:startTime="2595333" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exact model by regression: SSE=31969.99" xmpDM:startTime="2595333" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="2595333" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.4" xmpDM:startTime="2690533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Fit an AR(2) model to the data of Exercise 37.1." xmpDM:startTime="2690533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Determine parameters a0, a1, a2 and the SSE using multiple regression." xmpDM:startTime="2690533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Repeat the determination of parameters using autocorrelation function values." xmpDM:startTime="2690533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="2690533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.5" xmpDM:startTime="2691533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Fit an AR(3) model to the data of Exercise 37.1." xmpDM:startTime="2691533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Determine parameters a0, a1, a2, a3 and the SSE using multiple regression." xmpDM:startTime="2691533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="2691533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Determining the Order AR(p) ACF of AR(1) is an exponentially decreasing fn of k Fit AR(p) models of order p=0," xmpDM:startTime="2692833" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="1, 2, … Compute the (1-a)% confidence intervals of ap After some p, the last coefficients ap will not be" xmpDM:startTime="2692833" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="significant for all higher order models." xmpDM:startTime="2692833" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="This highest p is the order of the AR(p) model for the series." xmpDM:startTime="2692833" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="This sequence of last coefficients is also called &quot;Partial Autocorrelation Function (PACF)&quot; Lag k PACF(k) 0 TP_tmp TP_tmp p=8 TP_tmp" xmpDM:startTime="2692833" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="rk k" xmpDM:startTime="2692833" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.6" xmpDM:startTime="3073200" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="For the data of Example 37.1," xmpDM:startTime="3073200" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="we have: AR(1): AR(2): Similarly, AR(3): PACF at lags 1, 2, and 3 are: 0.503," xmpDM:startTime="3073200" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="-0.180," xmpDM:startTime="3073200" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="and 0.052" xmpDM:startTime="3073200" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(1) is appropriate." xmpDM:startTime="3073200" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="3073200" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Computing PACF = Determinant of M" xmpDM:startTime="3191533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Computing PACF (Cont)" xmpDM:startTime="3244433" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Computing PACF = Determinant of M" xmpDM:startTime="3440700" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Computing PACF (Cont)" xmpDM:startTime="3447067" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Computing PACF = Determinant of M" xmpDM:startTime="3473833" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Computing PACF (Cont)" xmpDM:startTime="3530467" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.6" xmpDM:startTime="3531000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Using the results of Exercises 37.1," xmpDM:startTime="3531000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="37.4," xmpDM:startTime="3531000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="and 37.5," xmpDM:startTime="3531000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="determine the partial autocorrelation function at lags 1, 2, 3 for the data of Exercise 37.1." xmpDM:startTime="3531000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Determine which values are significant." xmpDM:startTime="3531000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Based on this which AR(p) model will be appropriate for this data?" xmpDM:startTime="3531000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Moving Average (MA) Models Moving Average of order 1: MA(1) b0 is the mean of the time series." xmpDM:startTime="3531967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="The parameters b0 and b1 cannot be estimated using standard regression formulas since we do not know errors." xmpDM:startTime="3531967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="The errors depend on the parameters." xmpDM:startTime="3531967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="So the only way to find optimal b0 and b1 is by iteration." xmpDM:startTime="3531967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name=" Start with some suitable values and change b0 and b1 until SSE is minimized and average of errors is" xmpDM:startTime="3531967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="zero." xmpDM:startTime="3531967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="t TP_tmp" xmpDM:startTime="3531967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.6" xmpDM:startTime="3533600" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Using the results of Exercises 37.1," xmpDM:startTime="3533600" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="37.4," xmpDM:startTime="3533600" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="and 37.5," xmpDM:startTime="3533600" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="determine the partial autocorrelation function at lags 1, 2, 3 for the data of Exercise 37.1." xmpDM:startTime="3533600" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Determine which values are significant." xmpDM:startTime="3533600" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Based on this which AR(p) model will be appropriate for this data?" xmpDM:startTime="3533600" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Computing PACF (Cont)" xmpDM:startTime="3534100" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.6" xmpDM:startTime="3662500" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Using the results of Exercises 37.1," xmpDM:startTime="3662500" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="37.4," xmpDM:startTime="3662500" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="and 37.5," xmpDM:startTime="3662500" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="determine the partial autocorrelation function at lags 1, 2, 3 for the data of Exercise 37.1." xmpDM:startTime="3662500" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Determine which values are significant." xmpDM:startTime="3662500" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Based on this which AR(p) model will be appropriate for this data?" xmpDM:startTime="3662500" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Computing PACF (Cont)" xmpDM:startTime="3666733" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Computing PACF = Determinant of M" xmpDM:startTime="3690300" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Computing PACF (Cont)" xmpDM:startTime="3701167" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.6" xmpDM:startTime="3701833" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Using the results of Exercises 37.1," xmpDM:startTime="3701833" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="37.4," xmpDM:startTime="3701833" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="and 37.5," xmpDM:startTime="3701833" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="determine the partial autocorrelation function at lags 1, 2, 3 for the data of Exercise 37.1." xmpDM:startTime="3701833" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Determine which values are significant." xmpDM:startTime="3701833" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Based on this which AR(p) model will be appropriate for this data?" xmpDM:startTime="3701833" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Moving Average (MA) Models Moving Average of order 1: MA(1) b0 is the mean of the time series." xmpDM:startTime="3705600" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="The parameters b0 and b1 cannot be estimated using standard regression formulas since we do not know errors." xmpDM:startTime="3705600" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="The errors depend on the parameters." xmpDM:startTime="3705600" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="So the only way to find optimal b0 and b1 is by iteration." xmpDM:startTime="3705600" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name=" Start with some suitable values and change b0 and b1 until SSE is minimized and average of errors is" xmpDM:startTime="3705600" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="zero." xmpDM:startTime="3705600" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="t TP_tmp" xmpDM:startTime="3705600" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.6" xmpDM:startTime="3738267" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Using the results of Exercises 37.1," xmpDM:startTime="3738267" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="37.4," xmpDM:startTime="3738267" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="and 37.5," xmpDM:startTime="3738267" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="determine the partial autocorrelation function at lags 1, 2, 3 for the data of Exercise 37.1." xmpDM:startTime="3738267" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Determine which values are significant." xmpDM:startTime="3738267" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Based on this which AR(p) model will be appropriate for this data?" xmpDM:startTime="3738267" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Computing PACF (Cont)" xmpDM:startTime="3738467" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Computing PACF = Determinant of M" xmpDM:startTime="3738700" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.6" xmpDM:startTime="3738933" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="For the data of Example 37.1," xmpDM:startTime="3738933" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="we have: AR(1): AR(2): Similarly, AR(3): PACF at lags 1, 2, and 3 are: 0.503," xmpDM:startTime="3738933" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="-0.180," xmpDM:startTime="3738933" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="and 0.052" xmpDM:startTime="3738933" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(1) is appropriate." xmpDM:startTime="3738933" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="3738933" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Determining the Order AR(p) ACF of AR(1) is an exponentially decreasing fn of k Fit AR(p) models of order p=0," xmpDM:startTime="3739533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="1, 2, … Compute the (1-a)% confidence intervals of ap After some p, the last coefficients ap will not be" xmpDM:startTime="3739533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="significant for all higher order models." xmpDM:startTime="3739533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="This highest p is the order of the AR(p) model for the series." xmpDM:startTime="3739533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="This sequence of last coefficients is also called &quot;Partial Autocorrelation Function (PACF)&quot; Lag k PACF(k) 0 TP_tmp TP_tmp p=8 TP_tmp" xmpDM:startTime="3739533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="rk k" xmpDM:startTime="3739533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.5" xmpDM:startTime="3739900" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Fit an AR(3) model to the data of Exercise 37.1." xmpDM:startTime="3739900" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Determine parameters a0, a1, a2, a3 and the SSE using multiple regression." xmpDM:startTime="3739900" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="3739900" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.4" xmpDM:startTime="3740567" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Fit an AR(2) model to the data of Exercise 37.1." xmpDM:startTime="3740567" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Determine parameters a0, a1, a2 and the SSE using multiple regression." xmpDM:startTime="3740567" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Repeat the determination of parameters using autocorrelation function values." xmpDM:startTime="3740567" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="3740567" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.5" xmpDM:startTime="3741033" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Consider the data of Example 37.1" xmpDM:startTime="3741033" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="and fit an AR(2) model: SSE= 31979.39" xmpDM:startTime="3741033" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Small sample  Values of a0, a1, and a2 are approximate." xmpDM:startTime="3741033" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exact model by regression: SSE=31969.99" xmpDM:startTime="3741033" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="3741033" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation (Cont) All sums are from t=p to t=n and have n-p terms." xmpDM:startTime="3741633" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="For larger data sets: rk is the autocorrelation at lag k (i,j)th term = r|i-j|" xmpDM:startTime="3741633" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation (Cont) The equations can be written as: Note: All sums are for t=3 to n." xmpDM:startTime="3742433" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="n-2 terms." xmpDM:startTime="3742433" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Multiplying by the inverse of the first matrix, we get: TP_tmp TP_tmp" xmpDM:startTime="3742433" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation The coefficients ai's can be estimated by minimizing SSE using Multiple Linear Regression." xmpDM:startTime="3742967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Optimal a0, a1, and a2  Minimize SSE Set the first differential to zero: TP_tmp TP_tmp TP_tmp" xmpDM:startTime="3742967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation (Cont) The equations can be written as: Note: All sums are for t=3 to n." xmpDM:startTime="3744000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="n-2 terms." xmpDM:startTime="3744000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Multiplying by the inverse of the first matrix, we get: TP_tmp TP_tmp" xmpDM:startTime="3744000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation (Cont) All sums are from t=p to t=n and have n-p terms." xmpDM:startTime="3775800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="For larger data sets: rk is the autocorrelation at lag k (i,j)th term = r|i-j|" xmpDM:startTime="3775800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.5" xmpDM:startTime="3837000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Consider the data of Example 37.1" xmpDM:startTime="3837000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="and fit an AR(2) model: SSE= 31979.39" xmpDM:startTime="3837000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Small sample  Values of a0, a1, and a2 are approximate." xmpDM:startTime="3837000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exact model by regression: SSE=31969.99" xmpDM:startTime="3837000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="3837000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.4" xmpDM:startTime="3848900" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Fit an AR(2) model to the data of Exercise 37.1." xmpDM:startTime="3848900" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Determine parameters a0, a1, a2 and the SSE using multiple regression." xmpDM:startTime="3848900" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Repeat the determination of parameters using autocorrelation function values." xmpDM:startTime="3848900" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="3848900" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.5" xmpDM:startTime="3853967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Consider the data of Example 37.1" xmpDM:startTime="3853967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="and fit an AR(2) model: SSE= 31979.39" xmpDM:startTime="3853967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Small sample  Values of a0, a1, and a2 are approximate." xmpDM:startTime="3853967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exact model by regression: SSE=31969.99" xmpDM:startTime="3853967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="3853967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation (Cont) All sums are from t=p to t=n and have n-p terms." xmpDM:startTime="3874400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="For larger data sets: rk is the autocorrelation at lag k (i,j)th term = r|i-j|" xmpDM:startTime="3874400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation (Cont) The equations can be written as: Note: All sums are for t=3 to n." xmpDM:startTime="3874700" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="n-2 terms." xmpDM:startTime="3874700" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Multiplying by the inverse of the first matrix, we get: TP_tmp TP_tmp" xmpDM:startTime="3874700" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation The coefficients ai's can be estimated by minimizing SSE using Multiple Linear Regression." xmpDM:startTime="3874967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Optimal a0, a1, and a2  Minimize SSE Set the first differential to zero: TP_tmp TP_tmp TP_tmp" xmpDM:startTime="3874967" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Similarly, Or Using this notation, AR(p) model is: Here, Áp is a polynomial of degree p." xmpDM:startTime="3875233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="TP_tmp Backward Shift Operator TP_tmp TP_tmp TP_tmp TP_tmp TP_tmp" xmpDM:startTime="3875233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Model xt is a function of the last p values: AR(2): AR(3): TP_tmp TP_tmp TP_tmp" xmpDM:startTime="3875400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.3" xmpDM:startTime="3875833" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Conduct visual tests to verify whether or not the AR(1) model fitted in Exercise 37.1" xmpDM:startTime="3875833" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="is appropriate ." xmpDM:startTime="3875833" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="3875833" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Visual Tests (Cont) et TP_tmp e z -80 -60 -40 -20 0 20 40 60 80 -3 -2 -1 0" xmpDM:startTime="3876167" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="1 2 3 et t 3." xmpDM:startTime="3876167" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Errors et vs." xmpDM:startTime="3876167" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="predicted values 4." xmpDM:startTime="3876167" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Q-Q Plot of errors 5." xmpDM:startTime="3876167" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Errors et vs." xmpDM:startTime="3876167" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="t" xmpDM:startTime="3876167" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Visual Tests (Cont) 2." xmpDM:startTime="3876633" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Plot of xt vs." xmpDM:startTime="3876633" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="xt-1 xt-1 xt" xmpDM:startTime="3876633" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Visual Tests for AR(1) Models Plot xt as a function of t and look for trends xt vs." xmpDM:startTime="3877100" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="xt-1 for linearity Errors et vs." xmpDM:startTime="3877100" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="predicted values for additivity Q-Q Plot of errors for Normality Errors et vs." xmpDM:startTime="3877100" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="t for IID TP_tmp 1." xmpDM:startTime="3877100" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Plot of xt" xmpDM:startTime="3877100" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Assumptions for AR(1) Models xt is a Stationary process Linear relationship between successive values Normal Independent identically distributed errors: Normal" xmpDM:startTime="3877500" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="errors Independent errors Additive errors" xmpDM:startTime="3877500" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.2" xmpDM:startTime="3877867" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Determine autocorrelations at lag 0 through 2 for the data of Exercise 37.1" xmpDM:startTime="3877867" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="and determine which of these autocorrelations are significant at 95% confidence." xmpDM:startTime="3877867" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="3877867" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.3" xmpDM:startTime="3878300" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="For the data of Example 37.1:" xmpDM:startTime="3878300" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="n=50 TP_tmp r2 is not significantly different from zero." xmpDM:startTime="3878300" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="3878300" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="White Noise Autocorrelations It can be shown that autocorrelations for white noise are normally distributed with mean: and variance: Therefore," xmpDM:startTime="3879200" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="their 95% confidence interval is This is generally approximated as This confidence interval can be used to check if a" xmpDM:startTime="3879200" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="particular autocorrelation is zero." xmpDM:startTime="3879200" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="TP_tmp TP_tmp TP_tmp TP_tmp" xmpDM:startTime="3879200" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="White Noise (Cont) The autocorrelation function of a white noise sequence is a spike (± function) at k=0." xmpDM:startTime="3880067" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="The Laplace transform of a ± function is a constant." xmpDM:startTime="3880067" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="So in frequency domain white noise has a flat frequency spectrum." xmpDM:startTime="3880067" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="It was incorrectly assumed that white light has no color and, therefore, has a flat frequency spectrum and so random" xmpDM:startTime="3880067" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="noise with flat frequency spectrum was called white noise." xmpDM:startTime="3880067" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="t 0 f 0 Ref: http://en.wikipedia.org/wiki/Colors_of_noise" xmpDM:startTime="3880067" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="3880067" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="White Noise Errors et are normal independent and identically distributed (IID) with zero mean and variance ¾2 Such IID sequences" xmpDM:startTime="3880633" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="are called “white noise” sequences." xmpDM:startTime="3880633" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Properties: TP_tmp k 0" xmpDM:startTime="3880633" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.2" xmpDM:startTime="3881333" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="(Cont) Lag k Autocorrelation rk 0 1 2 1.0" xmpDM:startTime="3881333" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="3881333" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.2" xmpDM:startTime="3882500" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="(Cont) Note: Only 48 pairs of {xt, xt-1}  Divisor is 47" xmpDM:startTime="3882500" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.2" xmpDM:startTime="3884367" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="(Cont) Small Sample  and are slightly different." xmpDM:startTime="3884367" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Not so for large samples." xmpDM:startTime="3884367" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Divisor is 48 since we used sample mean calculated from the same sample" xmpDM:startTime="3884367" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.2" xmpDM:startTime="3886433" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="For the data of Example 37.1," xmpDM:startTime="3886433" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="the variance and covariance's at lag 1 and 2 are computed as follows:" xmpDM:startTime="3886433" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Autocorrelation Covariance of xt and xt-k = Auto-covariance at lag k For a stationary series: Statistical characteristics do not depend" xmpDM:startTime="3888500" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="upon time t." xmpDM:startTime="3888500" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Autocovariance depends only on lag k and not on time t Autocorrelation is dimensionless and is easier to interpret than" xmpDM:startTime="3888500" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="autocovariance." xmpDM:startTime="3888500" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="TP_tmp TP_tmp" xmpDM:startTime="3888500" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Stationary Process (Cont) Stationary = Standing in time  Distribution does not change with time." xmpDM:startTime="3889267" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Similarly, the joint distribution of xt and xt-k depends only on k not on t." xmpDM:startTime="3889267" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="The joint distribution of xt, xt-1, …, xt-k depends only on k not on t." xmpDM:startTime="3889267" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="3889267" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Stationary Process Each realization of a random process will be different: x is function of the realization i (space) and" xmpDM:startTime="3889933" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="time t: x(i, t) We can study the distribution of xt in space." xmpDM:startTime="3889933" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Each xt has a distribution, e.g.," xmpDM:startTime="3889933" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Normal If this same distribution (normal) with the same parameters ¹, ¾ applies to xt+1, xt+2, …, we say xt" xmpDM:startTime="3889933" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="is stationary." xmpDM:startTime="3889933" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="xt t TP_tmp" xmpDM:startTime="3889933" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.1" xmpDM:startTime="3891033" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Fit an AR(1) model to the following sample of 50 observations: 83, 86, 46, 34, 130, 109, 100, 81, 84," xmpDM:startTime="3891033" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="148, 93, 76, 69, 40, 50, 56, 63, 104, 35, 55, 124, 52, 55, 81, 33, 76, 83, 90, 94," xmpDM:startTime="3891033" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="37, -2, 33, 105, 133, 78, 50, 115, 149, 98, 110, 25, 82, 59, 80, 43, 58, 88, 78, 55," xmpDM:startTime="3891033" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="68." xmpDM:startTime="3891033" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Find a0, a1 and the minimum SSE." xmpDM:startTime="3891033" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="3891033" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.1" xmpDM:startTime="3894367" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="(Cont) The AR(1) model for the series is: The predicted value of x2 given x1 is: The actual observed value" xmpDM:startTime="3894367" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="of is 67." xmpDM:startTime="3894367" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Therefore, the prediction error is: Sum of squared errors SSE = 32995.57" xmpDM:startTime="3894367" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="TP_tmp TP_tmp TP_tmp TP_tmp" xmpDM:startTime="3894367" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.1" xmpDM:startTime="3957667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Fit an AR(1) model to the following sample of 50 observations: 83, 86, 46, 34, 130, 109, 100, 81, 84," xmpDM:startTime="3957667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="148, 93, 76, 69, 40, 50, 56, 63, 104, 35, 55, 124, 52, 55, 81, 33, 76, 83, 90, 94," xmpDM:startTime="3957667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="37, -2, 33, 105, 133, 78, 50, 115, 149, 98, 110, 25, 82, 59, 80, 43, 58, 88, 78, 55," xmpDM:startTime="3957667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="68." xmpDM:startTime="3957667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Find a0, a1 and the minimum SSE." xmpDM:startTime="3957667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="3957667" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Stationary Process Each realization of a random process will be different: x is function of the realization i (space) and" xmpDM:startTime="3958033" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="time t: x(i, t) We can study the distribution of xt in space." xmpDM:startTime="3958033" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Each xt has a distribution, e.g.," xmpDM:startTime="3958033" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Normal If this same distribution (normal) with the same parameters ¹, ¾ applies to xt+1, xt+2, …, we say xt" xmpDM:startTime="3958033" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="is stationary." xmpDM:startTime="3958033" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="xt t TP_tmp" xmpDM:startTime="3958033" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Stationary Process (Cont) Stationary = Standing in time  Distribution does not change with time." xmpDM:startTime="3958267" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Similarly, the joint distribution of xt and xt-k depends only on k not on t." xmpDM:startTime="3958267" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="The joint distribution of xt, xt-1, …, xt-k depends only on k not on t." xmpDM:startTime="3958267" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="3958267" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Autocorrelation Covariance of xt and xt-k = Auto-covariance at lag k For a stationary series: Statistical characteristics do not depend" xmpDM:startTime="3958533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="upon time t." xmpDM:startTime="3958533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Autocovariance depends only on lag k and not on time t Autocorrelation is dimensionless and is easier to interpret than" xmpDM:startTime="3958533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="autocovariance." xmpDM:startTime="3958533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="TP_tmp TP_tmp" xmpDM:startTime="3958533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.2" xmpDM:startTime="3958867" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="For the data of Example 37.1," xmpDM:startTime="3958867" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="the variance and covariance's at lag 1 and 2 are computed as follows:" xmpDM:startTime="3958867" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.2" xmpDM:startTime="3959133" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="(Cont) Small Sample  and are slightly different." xmpDM:startTime="3959133" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Not so for large samples." xmpDM:startTime="3959133" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Divisor is 48 since we used sample mean calculated from the same sample" xmpDM:startTime="3959133" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.2" xmpDM:startTime="3959467" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="(Cont) Note: Only 48 pairs of {xt, xt-1}  Divisor is 47" xmpDM:startTime="3959467" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.2" xmpDM:startTime="3960000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="(Cont) Lag k Autocorrelation rk 0 1 2 1.0" xmpDM:startTime="3960000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="3960000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="White Noise Errors et are normal independent and identically distributed (IID) with zero mean and variance ¾2 Such IID sequences" xmpDM:startTime="3960767" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="are called “white noise” sequences." xmpDM:startTime="3960767" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Properties: TP_tmp k 0" xmpDM:startTime="3960767" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="White Noise (Cont) The autocorrelation function of a white noise sequence is a spike (± function) at k=0." xmpDM:startTime="3961333" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="The Laplace transform of a ± function is a constant." xmpDM:startTime="3961333" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="So in frequency domain white noise has a flat frequency spectrum." xmpDM:startTime="3961333" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="It was incorrectly assumed that white light has no color and, therefore, has a flat frequency spectrum and so random" xmpDM:startTime="3961333" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="noise with flat frequency spectrum was called white noise." xmpDM:startTime="3961333" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="t 0 f 0 Ref: http://en.wikipedia.org/wiki/Colors_of_noise" xmpDM:startTime="3961333" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="3961333" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="White Noise Autocorrelations It can be shown that autocorrelations for white noise are normally distributed with mean: and variance: Therefore," xmpDM:startTime="3961867" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="their 95% confidence interval is This is generally approximated as This confidence interval can be used to check if a" xmpDM:startTime="3961867" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="particular autocorrelation is zero." xmpDM:startTime="3961867" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="TP_tmp TP_tmp TP_tmp TP_tmp" xmpDM:startTime="3961867" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.3" xmpDM:startTime="3962367" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="For the data of Example 37.1:" xmpDM:startTime="3962367" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="n=50 TP_tmp r2 is not significantly different from zero." xmpDM:startTime="3962367" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="3962367" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.2" xmpDM:startTime="3964167" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Determine autocorrelations at lag 0 through 2 for the data of Exercise 37.1" xmpDM:startTime="3964167" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="and determine which of these autocorrelations are significant at 95% confidence." xmpDM:startTime="3964167" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="3964167" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Assumptions for AR(1) Models xt is a Stationary process Linear relationship between successive values Normal Independent identically distributed errors: Normal" xmpDM:startTime="3964767" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="errors Independent errors Additive errors" xmpDM:startTime="3964767" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Visual Tests for AR(1) Models Plot xt as a function of t and look for trends xt vs." xmpDM:startTime="3965333" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="xt-1 for linearity Errors et vs." xmpDM:startTime="3965333" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="predicted values for additivity Q-Q Plot of errors for Normality Errors et vs." xmpDM:startTime="3965333" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="t for IID TP_tmp 1." xmpDM:startTime="3965333" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Plot of xt" xmpDM:startTime="3965333" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Visual Tests (Cont) 2." xmpDM:startTime="3966033" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Plot of xt vs." xmpDM:startTime="3966033" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="xt-1 xt-1 xt" xmpDM:startTime="3966033" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Visual Tests (Cont) et TP_tmp e z -80 -60 -40 -20 0 20 40 60 80 -3 -2 -1 0" xmpDM:startTime="3966533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="1 2 3 et t 3." xmpDM:startTime="3966533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Errors et vs." xmpDM:startTime="3966533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="predicted values 4." xmpDM:startTime="3966533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Q-Q Plot of errors 5." xmpDM:startTime="3966533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Errors et vs." xmpDM:startTime="3966533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="t" xmpDM:startTime="3966533" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.3" xmpDM:startTime="3967000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Conduct visual tests to verify whether or not the AR(1) model fitted in Exercise 37.1" xmpDM:startTime="3967000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="is appropriate ." xmpDM:startTime="3967000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="3967000" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Model xt is a function of the last p values: AR(2): AR(3): TP_tmp TP_tmp TP_tmp" xmpDM:startTime="3967433" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Similarly, Or Using this notation, AR(p) model is: Here, Áp is a polynomial of degree p." xmpDM:startTime="3967900" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="TP_tmp Backward Shift Operator TP_tmp TP_tmp TP_tmp TP_tmp TP_tmp" xmpDM:startTime="3967900" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation The coefficients ai's can be estimated by minimizing SSE using Multiple Linear Regression." xmpDM:startTime="3968900" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Optimal a0, a1, and a2  Minimize SSE Set the first differential to zero: TP_tmp TP_tmp TP_tmp" xmpDM:startTime="3968900" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation (Cont) The equations can be written as: Note: All sums are for t=3 to n." xmpDM:startTime="3969433" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="n-2 terms." xmpDM:startTime="3969433" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Multiplying by the inverse of the first matrix, we get: TP_tmp TP_tmp" xmpDM:startTime="3969433" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation (Cont) All sums are from t=p to t=n and have n-p terms." xmpDM:startTime="3970233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="For larger data sets: rk is the autocorrelation at lag k (i,j)th term = r|i-j|" xmpDM:startTime="3970233" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.5" xmpDM:startTime="3970867" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Consider the data of Example 37.1" xmpDM:startTime="3970867" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="and fit an AR(2) model: SSE= 31979.39" xmpDM:startTime="3970867" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Small sample  Values of a0, a1, and a2 are approximate." xmpDM:startTime="3970867" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exact model by regression: SSE=31969.99" xmpDM:startTime="3970867" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="3970867" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.4" xmpDM:startTime="3971633" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Fit an AR(2) model to the data of Exercise 37.1." xmpDM:startTime="3971633" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Determine parameters a0, a1, a2 and the SSE using multiple regression." xmpDM:startTime="3971633" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Repeat the determination of parameters using autocorrelation function values." xmpDM:startTime="3971633" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="3971633" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.5" xmpDM:startTime="3972400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Fit an AR(3) model to the data of Exercise 37.1." xmpDM:startTime="3972400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Determine parameters a0, a1, a2, a3 and the SSE using multiple regression." xmpDM:startTime="3972400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="3972400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Determining the Order AR(p) ACF of AR(1) is an exponentially decreasing fn of k Fit AR(p) models of order p=0," xmpDM:startTime="3972867" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="1, 2, … Compute the (1-a)% confidence intervals of ap After some p, the last coefficients ap will not be" xmpDM:startTime="3972867" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="significant for all higher order models." xmpDM:startTime="3972867" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="This highest p is the order of the AR(p) model for the series." xmpDM:startTime="3972867" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="This sequence of last coefficients is also called &quot;Partial Autocorrelation Function (PACF)&quot; Lag k PACF(k) 0 TP_tmp TP_tmp p=8 TP_tmp" xmpDM:startTime="3972867" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="rk k" xmpDM:startTime="3972867" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.6" xmpDM:startTime="3973400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="For the data of Example 37.1," xmpDM:startTime="3973400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="we have: AR(1): AR(2): Similarly, AR(3): PACF at lags 1, 2, and 3 are: 0.503," xmpDM:startTime="3973400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="-0.180," xmpDM:startTime="3973400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="and 0.052" xmpDM:startTime="3973400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(1) is appropriate." xmpDM:startTime="3973400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="" xmpDM:startTime="3973400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Computing PACF = Determinant of M" xmpDM:startTime="3973867" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Computing PACF (Cont)" xmpDM:startTime="3974067" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.6" xmpDM:startTime="3974367" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Using the results of Exercises 37.1," xmpDM:startTime="3974367" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="37.4," xmpDM:startTime="3974367" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="and 37.5," xmpDM:startTime="3974367" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="determine the partial autocorrelation function at lags 1, 2, 3 for the data of Exercise 37.1." xmpDM:startTime="3974367" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Determine which values are significant." xmpDM:startTime="3974367" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Based on this which AR(p) model will be appropriate for this data?" xmpDM:startTime="3974367" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Moving Average (MA) Models Moving Average of order 1: MA(1) b0 is the mean of the time series." xmpDM:startTime="3974700" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="The parameters b0 and b1 cannot be estimated using standard regression formulas since we do not know errors." xmpDM:startTime="3974700" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="The errors depend on the parameters." xmpDM:startTime="3974700" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="So the only way to find optimal b0 and b1 is by iteration." xmpDM:startTime="3974700" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name=" Start with some suitable values and change b0 and b1 until SSE is minimized and average of errors is" xmpDM:startTime="3974700" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="zero." xmpDM:startTime="3974700" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="t TP_tmp" xmpDM:startTime="3974700" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.4" xmpDM:startTime="4107167" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Consider the data of Example 37.1." xmpDM:startTime="4107167" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="For this data: We start with b0 = 67.72," xmpDM:startTime="4107167" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="b1=0.4," xmpDM:startTime="4107167" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Assuming e0=0, compute all the errors and SSE." xmpDM:startTime="4107167" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="and SSE = 33542.8" xmpDM:startTime="4107167" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="We then adjust a0 and b1 until SSE is minimized and mean error is close to zero." xmpDM:startTime="4107167" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="TP_tmp TP_tmp …" xmpDM:startTime="4107167" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.4" xmpDM:startTime="4174767" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="(Cont) The steps are: Starting with and trying various values of b1." xmpDM:startTime="4174767" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="SSE is minimum at b1=0.475." xmpDM:startTime="4174767" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="SSE= 33221.06" xmpDM:startTime="4174767" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="TP_tmp" xmpDM:startTime="4174767" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.4" xmpDM:startTime="4289833" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="(Cont) Keeping b1=0.475," xmpDM:startTime="4289833" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="try neighboring values of b0 to get average error as close to zero as possible." xmpDM:startTime="4289833" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="b0= 67.475" xmpDM:startTime="4289833" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="gives =-0.001" xmpDM:startTime="4289833" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="SSE=33221.93" xmpDM:startTime="4289833" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="TP_tmp" xmpDM:startTime="4289833" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="MA(q) Models Moving Average of order 1: MA(1) Moving Average of order 2: MA(2) Moving Average of order q: MA(q)" xmpDM:startTime="4291800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Moving Average of order 0: MA(0) (Note: This is also AR(0)) xt-b0 is a white noise." xmpDM:startTime="4291800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="b0 is the mean of the time series." xmpDM:startTime="4291800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="t TP_tmp TP_tmp TP_tmp TP_tmp" xmpDM:startTime="4291800" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.4" xmpDM:startTime="4293167" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="(Cont) Keeping b1=0.475," xmpDM:startTime="4293167" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="try neighboring values of b0 to get average error as close to zero as possible." xmpDM:startTime="4293167" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="b0= 67.475" xmpDM:startTime="4293167" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="gives =-0.001" xmpDM:startTime="4293167" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="SSE=33221.93" xmpDM:startTime="4293167" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="TP_tmp" xmpDM:startTime="4293167" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.4" xmpDM:startTime="4293400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="(Cont) The steps are: Starting with and trying various values of b1." xmpDM:startTime="4293400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="SSE is minimum at b1=0.475." xmpDM:startTime="4293400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="SSE= 33221.06" xmpDM:startTime="4293400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="TP_tmp" xmpDM:startTime="4293400" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.4" xmpDM:startTime="4294067" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Consider the data of Example 37.1." xmpDM:startTime="4294067" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="For this data: We start with b0 = 67.72," xmpDM:startTime="4294067" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="b1=0.4," xmpDM:startTime="4294067" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Assuming e0=0, compute all the errors and SSE." xmpDM:startTime="4294067" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="and SSE = 33542.8" xmpDM:startTime="4294067" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="We then adjust a0 and b1 until SSE is minimized and mean error is close to zero." xmpDM:startTime="4294067" xmpDM:duration="1000"/></rdf:li><rdf:li><rdf:Description xmpDM:name="TP_tmp TP_tmp …" xmpDM:startTime="4294067" xmpDM:duration="1000"/></rdf:li></rdf:Seq>
                     </xmpDM:markers>
                  </rdf:Description>
               </rdf:li>
               <rdf:li>
                  <rdf:Description xmpDM:trackType="TableOfContents" xmpDM:frameRate="f1000" xmpDM:trackName="Table of Contents">
                     <xmpDM:markers>
                        <rdf:Seq>
                           <rdf:li><rdf:Description xmpDM:name="Overview" xmpDM:startTime="2100" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="0" tscDM:imageoffset="0" tscDM:imagerect="0, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Stochastic Processes" xmpDM:startTime="20233" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="1" tscDM:imageoffset="0" tscDM:imagerect="75, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Stochastic Processes: Key Questions" xmpDM:startTime="78967" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="2" tscDM:imageoffset="0" tscDM:imagerect="150, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Stochastic Processes : Key Questions (Cont)" xmpDM:startTime="125700" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="3" tscDM:imageoffset="0" tscDM:imagerect="225, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="What is a Time Series" xmpDM:startTime="179067" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="4" tscDM:imageoffset="0" tscDM:imagerect="300, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Autoregressive Models" xmpDM:startTime="216333" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="5" tscDM:imageoffset="0" tscDM:imagerect="375, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.1" xmpDM:startTime="345000" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="6" tscDM:imageoffset="0" tscDM:imagerect="450, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Autoregressive Models" xmpDM:startTime="360733" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="7" tscDM:imageoffset="0" tscDM:imagerect="525, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.1" xmpDM:startTime="365300" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="8" tscDM:imageoffset="0" tscDM:imagerect="600, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.1 (Cont)" xmpDM:startTime="436867" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="9" tscDM:imageoffset="0" tscDM:imagerect="675, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.1" xmpDM:startTime="483300" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="10" tscDM:imageoffset="0" tscDM:imagerect="750, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.1 (Cont)" xmpDM:startTime="487500" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="11" tscDM:imageoffset="0" tscDM:imagerect="825, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.1" xmpDM:startTime="495567" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="12" tscDM:imageoffset="0" tscDM:imagerect="900, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.1 (Cont)" xmpDM:startTime="499333" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="13" tscDM:imageoffset="0" tscDM:imagerect="975, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.1" xmpDM:startTime="532800" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="14" tscDM:imageoffset="0" tscDM:imagerect="1050, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.1 (Cont)" xmpDM:startTime="549567" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="15" tscDM:imageoffset="0" tscDM:imagerect="1125, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.1" xmpDM:startTime="550133" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="16" tscDM:imageoffset="0" tscDM:imagerect="1200, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.1 (Cont)" xmpDM:startTime="585167" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="17" tscDM:imageoffset="0" tscDM:imagerect="1275, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.1" xmpDM:startTime="587167" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="18" tscDM:imageoffset="0" tscDM:imagerect="1350, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Stationary Process" xmpDM:startTime="591433" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="19" tscDM:imageoffset="0" tscDM:imagerect="1425, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Stationary Process (Cont)" xmpDM:startTime="868033" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="20" tscDM:imageoffset="0" tscDM:imagerect="1500, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Autocorrelation" xmpDM:startTime="913200" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="21" tscDM:imageoffset="0" tscDM:imagerect="1575, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.2" xmpDM:startTime="1022767" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="22" tscDM:imageoffset="0" tscDM:imagerect="1650, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.2 (Cont)" xmpDM:startTime="1053300" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="23" tscDM:imageoffset="0" tscDM:imagerect="1725, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.2 (Cont)" xmpDM:startTime="1192933" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="24" tscDM:imageoffset="0" tscDM:imagerect="1800, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.2 (Cont)" xmpDM:startTime="1267400" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="25" tscDM:imageoffset="0" tscDM:imagerect="1875, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.2 (Cont)" xmpDM:startTime="1272933" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="26" tscDM:imageoffset="0" tscDM:imagerect="1950, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.2 (Cont)" xmpDM:startTime="1283267" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="27" tscDM:imageoffset="0" tscDM:imagerect="2025, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="White Noise" xmpDM:startTime="1328000" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="28" tscDM:imageoffset="0" tscDM:imagerect="2100, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="White Noise (Cont)" xmpDM:startTime="1370833" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="29" tscDM:imageoffset="0" tscDM:imagerect="2175, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="White Noise" xmpDM:startTime="1377500" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="30" tscDM:imageoffset="0" tscDM:imagerect="2250, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="White Noise (Cont)" xmpDM:startTime="1426367" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="31" tscDM:imageoffset="0" tscDM:imagerect="2325, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="White Noise Autocorrelations" xmpDM:startTime="1543433" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="32" tscDM:imageoffset="0" tscDM:imagerect="2400, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.3" xmpDM:startTime="1668700" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="33" tscDM:imageoffset="0" tscDM:imagerect="2475, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.2" xmpDM:startTime="1833667" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="34" tscDM:imageoffset="0" tscDM:imagerect="2550, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Assumptions for AR(1) Models" xmpDM:startTime="1845900" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="35" tscDM:imageoffset="0" tscDM:imagerect="2625, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Visual Tests for AR(1) Models" xmpDM:startTime="1950500" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="36" tscDM:imageoffset="0" tscDM:imagerect="2700, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Visual Tests (Cont)" xmpDM:startTime="1994033" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="37" tscDM:imageoffset="0" tscDM:imagerect="2775, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Visual Tests (Cont)" xmpDM:startTime="2015767" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="38" tscDM:imageoffset="0" tscDM:imagerect="2850, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.3" xmpDM:startTime="2071133" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="39" tscDM:imageoffset="0" tscDM:imagerect="2925, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Model" xmpDM:startTime="2074400" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="40" tscDM:imageoffset="0" tscDM:imagerect="3000, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Backward Shift Operator" xmpDM:startTime="2157600" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="41" tscDM:imageoffset="0" tscDM:imagerect="3075, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="          AR(p) Parameter Estimation" xmpDM:startTime="2290833" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="42" tscDM:imageoffset="0" tscDM:imagerect="3150, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation (Cont)" xmpDM:startTime="2312567" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="43" tscDM:imageoffset="0" tscDM:imagerect="3225, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation (Cont)" xmpDM:startTime="2331133" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="44" tscDM:imageoffset="0" tscDM:imagerect="3300, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation (Cont)" xmpDM:startTime="2415033" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="45" tscDM:imageoffset="0" tscDM:imagerect="3375, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="          AR(p) Parameter Estimation" xmpDM:startTime="2415767" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="46" tscDM:imageoffset="0" tscDM:imagerect="3450, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Backward Shift Operator" xmpDM:startTime="2416533" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="47" tscDM:imageoffset="0" tscDM:imagerect="3525, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Model" xmpDM:startTime="2419300" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="48" tscDM:imageoffset="0" tscDM:imagerect="3600, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Backward Shift Operator" xmpDM:startTime="2451667" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="49" tscDM:imageoffset="0" tscDM:imagerect="3675, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="          AR(p) Parameter Estimation" xmpDM:startTime="2451933" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="50" tscDM:imageoffset="0" tscDM:imagerect="3750, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation (Cont)" xmpDM:startTime="2452767" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="51" tscDM:imageoffset="0" tscDM:imagerect="3825, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation (Cont)" xmpDM:startTime="2453333" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="52" tscDM:imageoffset="0" tscDM:imagerect="3900, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.5" xmpDM:startTime="2481800" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="53" tscDM:imageoffset="0" tscDM:imagerect="3975, 0, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation (Cont)" xmpDM:startTime="2557333" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="54" tscDM:imageoffset="0" tscDM:imagerect="50, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.5" xmpDM:startTime="2579533" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="55" tscDM:imageoffset="0" tscDM:imagerect="125, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation (Cont)" xmpDM:startTime="2588667" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="56" tscDM:imageoffset="0" tscDM:imagerect="200, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation (Cont)" xmpDM:startTime="2588900" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="57" tscDM:imageoffset="0" tscDM:imagerect="275, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="          AR(p) Parameter Estimation" xmpDM:startTime="2592867" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="58" tscDM:imageoffset="0" tscDM:imagerect="350, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation (Cont)" xmpDM:startTime="2594467" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="59" tscDM:imageoffset="0" tscDM:imagerect="425, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation (Cont)" xmpDM:startTime="2594900" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="60" tscDM:imageoffset="0" tscDM:imagerect="500, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.5" xmpDM:startTime="2595333" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="61" tscDM:imageoffset="0" tscDM:imagerect="575, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.4" xmpDM:startTime="2690533" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="62" tscDM:imageoffset="0" tscDM:imagerect="650, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.5" xmpDM:startTime="2691533" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="63" tscDM:imageoffset="0" tscDM:imagerect="725, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="        Determining the Order AR(p)" xmpDM:startTime="2692833" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="64" tscDM:imageoffset="0" tscDM:imagerect="800, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.6" xmpDM:startTime="3073200" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="65" tscDM:imageoffset="0" tscDM:imagerect="875, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Computing PACF" xmpDM:startTime="3191533" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="66" tscDM:imageoffset="0" tscDM:imagerect="950, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Computing PACF (Cont)" xmpDM:startTime="3244433" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="67" tscDM:imageoffset="0" tscDM:imagerect="1025, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Computing PACF" xmpDM:startTime="3440700" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="68" tscDM:imageoffset="0" tscDM:imagerect="1100, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Computing PACF (Cont)" xmpDM:startTime="3447067" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="69" tscDM:imageoffset="0" tscDM:imagerect="1175, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Computing PACF" xmpDM:startTime="3473833" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="70" tscDM:imageoffset="0" tscDM:imagerect="1250, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Computing PACF (Cont)" xmpDM:startTime="3530467" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="71" tscDM:imageoffset="0" tscDM:imagerect="1325, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.6" xmpDM:startTime="3531000" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="72" tscDM:imageoffset="0" tscDM:imagerect="1400, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="       Moving Average (MA) Models" xmpDM:startTime="3531967" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="73" tscDM:imageoffset="0" tscDM:imagerect="1475, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.6" xmpDM:startTime="3533600" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="74" tscDM:imageoffset="0" tscDM:imagerect="1550, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Computing PACF (Cont)" xmpDM:startTime="3534100" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="75" tscDM:imageoffset="0" tscDM:imagerect="1625, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.6" xmpDM:startTime="3662500" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="76" tscDM:imageoffset="0" tscDM:imagerect="1700, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Computing PACF (Cont)" xmpDM:startTime="3666733" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="77" tscDM:imageoffset="0" tscDM:imagerect="1775, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Computing PACF" xmpDM:startTime="3690300" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="78" tscDM:imageoffset="0" tscDM:imagerect="1850, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Computing PACF (Cont)" xmpDM:startTime="3701167" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="79" tscDM:imageoffset="0" tscDM:imagerect="1925, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.6" xmpDM:startTime="3701833" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="80" tscDM:imageoffset="0" tscDM:imagerect="2000, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="       Moving Average (MA) Models" xmpDM:startTime="3705600" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="81" tscDM:imageoffset="0" tscDM:imagerect="2075, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.6" xmpDM:startTime="3738267" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="82" tscDM:imageoffset="0" tscDM:imagerect="2150, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Computing PACF (Cont)" xmpDM:startTime="3738467" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="83" tscDM:imageoffset="0" tscDM:imagerect="2225, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Computing PACF" xmpDM:startTime="3738700" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="84" tscDM:imageoffset="0" tscDM:imagerect="2300, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.6" xmpDM:startTime="3738933" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="85" tscDM:imageoffset="0" tscDM:imagerect="2375, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="        Determining the Order AR(p)" xmpDM:startTime="3739533" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="86" tscDM:imageoffset="0" tscDM:imagerect="2450, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.5" xmpDM:startTime="3739900" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="87" tscDM:imageoffset="0" tscDM:imagerect="2525, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.4" xmpDM:startTime="3740567" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="88" tscDM:imageoffset="0" tscDM:imagerect="2600, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.5" xmpDM:startTime="3741033" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="89" tscDM:imageoffset="0" tscDM:imagerect="2675, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation (Cont)" xmpDM:startTime="3741633" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="90" tscDM:imageoffset="0" tscDM:imagerect="2750, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation (Cont)" xmpDM:startTime="3742433" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="91" tscDM:imageoffset="0" tscDM:imagerect="2825, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="          AR(p) Parameter Estimation" xmpDM:startTime="3742967" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="92" tscDM:imageoffset="0" tscDM:imagerect="2900, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation (Cont)" xmpDM:startTime="3744000" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="93" tscDM:imageoffset="0" tscDM:imagerect="2975, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation (Cont)" xmpDM:startTime="3775800" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="94" tscDM:imageoffset="0" tscDM:imagerect="3050, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.5" xmpDM:startTime="3837000" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="95" tscDM:imageoffset="0" tscDM:imagerect="3125, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.4" xmpDM:startTime="3848900" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="96" tscDM:imageoffset="0" tscDM:imagerect="3200, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.5" xmpDM:startTime="3853967" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="97" tscDM:imageoffset="0" tscDM:imagerect="3275, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation (Cont)" xmpDM:startTime="3874400" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="98" tscDM:imageoffset="0" tscDM:imagerect="3350, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation (Cont)" xmpDM:startTime="3874700" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="99" tscDM:imageoffset="0" tscDM:imagerect="3425, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="          AR(p) Parameter Estimation" xmpDM:startTime="3874967" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="100" tscDM:imageoffset="0" tscDM:imagerect="3500, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Backward Shift Operator" xmpDM:startTime="3875233" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="101" tscDM:imageoffset="0" tscDM:imagerect="3575, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Model" xmpDM:startTime="3875400" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="102" tscDM:imageoffset="0" tscDM:imagerect="3650, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.3" xmpDM:startTime="3875833" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="103" tscDM:imageoffset="0" tscDM:imagerect="3725, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Visual Tests (Cont)" xmpDM:startTime="3876167" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="104" tscDM:imageoffset="0" tscDM:imagerect="3800, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Visual Tests (Cont)" xmpDM:startTime="3876633" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="105" tscDM:imageoffset="0" tscDM:imagerect="3875, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Visual Tests for AR(1) Models" xmpDM:startTime="3877100" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="106" tscDM:imageoffset="0" tscDM:imagerect="3950, 56, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Assumptions for AR(1) Models" xmpDM:startTime="3877500" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="107" tscDM:imageoffset="0" tscDM:imagerect="25, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.2" xmpDM:startTime="3877867" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="108" tscDM:imageoffset="0" tscDM:imagerect="100, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.3" xmpDM:startTime="3878300" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="109" tscDM:imageoffset="0" tscDM:imagerect="175, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="White Noise Autocorrelations" xmpDM:startTime="3879200" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="110" tscDM:imageoffset="0" tscDM:imagerect="250, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="White Noise (Cont)" xmpDM:startTime="3880067" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="111" tscDM:imageoffset="0" tscDM:imagerect="325, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="White Noise" xmpDM:startTime="3880633" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="112" tscDM:imageoffset="0" tscDM:imagerect="400, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.2 (Cont)" xmpDM:startTime="3881333" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="113" tscDM:imageoffset="0" tscDM:imagerect="475, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.2 (Cont)" xmpDM:startTime="3882500" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="114" tscDM:imageoffset="0" tscDM:imagerect="550, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.2 (Cont)" xmpDM:startTime="3884367" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="115" tscDM:imageoffset="0" tscDM:imagerect="625, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.2" xmpDM:startTime="3886433" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="116" tscDM:imageoffset="0" tscDM:imagerect="700, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Autocorrelation" xmpDM:startTime="3888500" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="117" tscDM:imageoffset="0" tscDM:imagerect="775, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Stationary Process (Cont)" xmpDM:startTime="3889267" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="118" tscDM:imageoffset="0" tscDM:imagerect="850, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Stationary Process" xmpDM:startTime="3889933" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="119" tscDM:imageoffset="0" tscDM:imagerect="925, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.1" xmpDM:startTime="3891033" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="120" tscDM:imageoffset="0" tscDM:imagerect="1000, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.1 (Cont)" xmpDM:startTime="3894367" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="121" tscDM:imageoffset="0" tscDM:imagerect="1075, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.1" xmpDM:startTime="3957667" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="122" tscDM:imageoffset="0" tscDM:imagerect="1150, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Stationary Process" xmpDM:startTime="3958033" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="123" tscDM:imageoffset="0" tscDM:imagerect="1225, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Stationary Process (Cont)" xmpDM:startTime="3958267" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="124" tscDM:imageoffset="0" tscDM:imagerect="1300, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Autocorrelation" xmpDM:startTime="3958533" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="125" tscDM:imageoffset="0" tscDM:imagerect="1375, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.2" xmpDM:startTime="3958867" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="126" tscDM:imageoffset="0" tscDM:imagerect="1450, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.2 (Cont)" xmpDM:startTime="3959133" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="127" tscDM:imageoffset="0" tscDM:imagerect="1525, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.2 (Cont)" xmpDM:startTime="3959467" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="128" tscDM:imageoffset="0" tscDM:imagerect="1600, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.2 (Cont)" xmpDM:startTime="3960000" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="129" tscDM:imageoffset="0" tscDM:imagerect="1675, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="White Noise" xmpDM:startTime="3960767" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="130" tscDM:imageoffset="0" tscDM:imagerect="1750, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="White Noise (Cont)" xmpDM:startTime="3961333" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="131" tscDM:imageoffset="0" tscDM:imagerect="1825, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="White Noise Autocorrelations" xmpDM:startTime="3961867" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="132" tscDM:imageoffset="0" tscDM:imagerect="1900, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.3" xmpDM:startTime="3962367" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="133" tscDM:imageoffset="0" tscDM:imagerect="1975, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.2" xmpDM:startTime="3964167" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="134" tscDM:imageoffset="0" tscDM:imagerect="2050, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Assumptions for AR(1) Models" xmpDM:startTime="3964767" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="135" tscDM:imageoffset="0" tscDM:imagerect="2125, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Visual Tests for AR(1) Models" xmpDM:startTime="3965333" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="136" tscDM:imageoffset="0" tscDM:imagerect="2200, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Visual Tests (Cont)" xmpDM:startTime="3966033" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="137" tscDM:imageoffset="0" tscDM:imagerect="2275, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Visual Tests (Cont)" xmpDM:startTime="3966533" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="138" tscDM:imageoffset="0" tscDM:imagerect="2350, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.3" xmpDM:startTime="3967000" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="139" tscDM:imageoffset="0" tscDM:imagerect="2425, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Model" xmpDM:startTime="3967433" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="140" tscDM:imageoffset="0" tscDM:imagerect="2500, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Backward Shift Operator" xmpDM:startTime="3967900" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="141" tscDM:imageoffset="0" tscDM:imagerect="2575, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="          AR(p) Parameter Estimation" xmpDM:startTime="3968900" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="142" tscDM:imageoffset="0" tscDM:imagerect="2650, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation (Cont)" xmpDM:startTime="3969433" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="143" tscDM:imageoffset="0" tscDM:imagerect="2725, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="AR(p) Parameter Estimation (Cont)" xmpDM:startTime="3970233" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="144" tscDM:imageoffset="0" tscDM:imagerect="2800, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.5" xmpDM:startTime="3970867" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="145" tscDM:imageoffset="0" tscDM:imagerect="2875, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.4" xmpDM:startTime="3971633" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="146" tscDM:imageoffset="0" tscDM:imagerect="2950, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.5" xmpDM:startTime="3972400" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="147" tscDM:imageoffset="0" tscDM:imagerect="3025, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="        Determining the Order AR(p)" xmpDM:startTime="3972867" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="148" tscDM:imageoffset="0" tscDM:imagerect="3100, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.6" xmpDM:startTime="3973400" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="149" tscDM:imageoffset="0" tscDM:imagerect="3175, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Computing PACF" xmpDM:startTime="3973867" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="150" tscDM:imageoffset="0" tscDM:imagerect="3250, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Computing PACF (Cont)" xmpDM:startTime="3974067" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="151" tscDM:imageoffset="0" tscDM:imagerect="3325, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Exercise 37.6" xmpDM:startTime="3974367" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="152" tscDM:imageoffset="0" tscDM:imagerect="3400, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="       Moving Average (MA) Models" xmpDM:startTime="3974700" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="153" tscDM:imageoffset="0" tscDM:imagerect="3475, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.4" xmpDM:startTime="4107167" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="154" tscDM:imageoffset="0" tscDM:imagerect="3550, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.4 (Cont)" xmpDM:startTime="4174767" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="155" tscDM:imageoffset="0" tscDM:imagerect="3625, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.4 (Cont)" xmpDM:startTime="4289833" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="156" tscDM:imageoffset="0" tscDM:imagerect="3700, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="MA(q) Models" xmpDM:startTime="4291800" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="157" tscDM:imageoffset="0" tscDM:imagerect="3775, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.4 (Cont)" xmpDM:startTime="4293167" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="158" tscDM:imageoffset="0" tscDM:imagerect="3850, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.4 (Cont)" xmpDM:startTime="4293400" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="159" tscDM:imageoffset="0" tscDM:imagerect="3925, 112, 75, 56"/></rdf:li><rdf:li><rdf:Description xmpDM:name="Example 37.4" xmpDM:startTime="4294067" tscDM:image="k_37tsa1_Thumbnails.png" tscDM:imageindex="160" tscDM:imageoffset="0" tscDM:imagerect="0, 168, 75, 56"/></rdf:li></rdf:Seq>
                     </xmpDM:markers>
                  </rdf:Description>
               </rdf:li>
            </rdf:Bag>
         </xmpDM:Tracks>
         <tscDM:controller>
            <rdf:Description xmpDM:name="tscplayer">
               <tscDM:parameters>
                  <rdf:Bag>
                     <rdf:li xmpDM:name="autohide" xmpDM:value="true"/><rdf:li xmpDM:name="autoplay" xmpDM:value="false"/><rdf:li xmpDM:name="loop" xmpDM:value="false"/><rdf:li xmpDM:name="searchable" xmpDM:value="true"/><rdf:li xmpDM:name="captionsenabled" xmpDM:value="false"/><rdf:li xmpDM:name="sidebarenabled" xmpDM:value="false"/><rdf:li xmpDM:name="unicodeenabled" xmpDM:value="false"/><rdf:li xmpDM:name="backgroundcolor" xmpDM:value="000000"/><rdf:li xmpDM:name="sidebarlocation" xmpDM:value="left"/><rdf:li xmpDM:name="endaction" xmpDM:value="stop"/><rdf:li xmpDM:name="endactionparam" xmpDM:value="true"/><rdf:li xmpDM:name="locale" xmpDM:value="en-US"/></rdf:Bag>
               </tscDM:parameters>
               <tscDM:controllerText>
                  <rdf:Bag>
                  </rdf:Bag>
               </tscDM:controllerText>
            </rdf:Description>
         </tscDM:controller>
         <tscDM:contentList>
            <rdf:Description>
               <tscDM:files>
                  <rdf:Seq>
                     <rdf:li xmpDM:name="0" xmpDM:value="k_37tsa1.mp4"/><rdf:li xmpDM:name="1" xmpDM:value="k_37tsa1_First_Frame.png"/><rdf:li xmpDM:name="2" xmpDM:value="k_37tsa1_Thumbnails.png"/></rdf:Seq>
               </tscDM:files>
            </rdf:Description>
         </tscDM:contentList>
      </rdf:Description>
   </rdf:RDF>
</x:xmpmeta>