E2-245a - X ∗ t other than X t − V t In e f ect we need to& nd the part of V t that is uncorrelated with X t To do so we construct W t = aV

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
Economics 245A Exercise 2 Consider the errors-in-variables model (that is, measurement error in the re- gressor) Y t = X t β + U t , in which the regressor is latent. We observe X t = X t + V t . We assume that X t , U t and V t are independent Gaussian random variables with zero mean. a) For the ordinary least squares estimator P n t =1 X t Y t P n t =1 X 2 t , discuss why replacement of X t with X t V t results in an expression that we cannot easily use to calculate the exact nite sample bias. b) To evaluate the exact nite sample bias, we use an expression for
Background image of page 1
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: X ∗ t other than X t − V t . In e f ect, we need to & nd the part of V t that is uncorrelated with X t . To do so, we construct W t = aV t − bX ∗ t , for values of a and b to be determined. The values of a and b must be such that E ( X t W t ) = 0 and also satisfy X ∗ t = cX t − W t . Find the values of ( a,b, c ) and use the resultant W t to derive the exact & nite sample bias of the OLS estimator....
View Full Document

This note was uploaded on 12/26/2011 for the course ECON 245a taught by Professor Staff during the Fall '08 term at UCSB.

Ask a homework question - tutors are online