This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: 3862Problem Set #3Spring 2008Due April 231) Problem 11.2 in the textbook2) Problem 11.4 in the textbook.3)You want to estimate the model , where is strictly exogenous, i.e.,, but is serially correlated. (a)You believe that the serial correlation is of the following form, where is “white noise” (i.e., it is mean independent ofand , it has constant variance, and it is serially uncorrelated). Explain how you wouldtransform the model to estimate the parameters using GLS. Be specific.(b)Suppose that you change your assumptions and now believe that the variance of is notconstant. Instead, it is . All other assumptions are as in part (a). Explain nowhow you would estimate the parameters efficiently. Be specific.4)Use the data in TRAFFIC2.DTA for this exercise. This data file contains 108 monthlyobservations on automobile accidents, traffic laws and some other variables forCalifornia from January 1981 through December 1989....
View
Full Document
 Spring '08
 Walsh
 Statistics, Variance, Statistical significance, seat belt law, heteroskedasticityrobust standard errors

Click to edit the document details