Lecture 16 Large sample results (Consistency)

# Lecture 16 Large sample results (Consistency) - Economics...

This preview shows pages 1–6. Sign up to view the full content.

Economics 326 Methods of Empirical Research in Economics Lecture 16: Large sample results: Consistency Vadim Marmer University of British Columbia March 29, 2011

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Why we need the large sample theory I We have shown that the OLS estimator ˆ β has some desirable properties: I ˆ β is unbiased if the errors are strongly exogenous: E ( U j X ) = 0 . I If in addition the errors are homoskedastic then d Var & ˆ β ± = s 2 / n i = 1 ( X i & ¯ X ) 2 is an unbiased estimator of the conditional variance of the OLS estimator ˆ β . I If in addition the errors are normally distributed (given X ) then T = & ˆ β & β ± / q d & ˆ β ± has a t distribution which can be used for hypotheses testing. 1/20
Why we need the large sample theory I If the errors are only weakly exogenous: E ( X i U i ) = 0 , the OLS estimator is in general biased. I If the errors are heteroskedastic: E & U 2 i j X i ± = h ( X i ) , the "usual" variance formula is invalid; we also do not have an unbiased estimator for the variance in this case. I If the errors are not normally distributed conditional on X then T - and F -statistics do not have t and F distributions under the null hypothesis. I The asymptotic or large sample theory allows us to derive approximate properties and distributions of estimators and test statistics by assuming that the sample size n is very large. 2/20

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Convergence in probability and LLN I Let θ n be a sequence of random variables indexed by the sample size n . We say that θ n converges in probability if lim n ! P ( j θ n & θ j ± ε ) = 0 for all ε > 0 . I We denote this as θ n ! p θ or p lim θ n = θ . I An example of convergence in probability is a Law of Large Numbers (LLN): Let X 1 , X 2 , . . . , X n be a random sample such that E ( X i ) = μ for all i = 1 , . . . , n , and de&ne ¯ X n = 1 n n i = 1 X i . Then, under certain conditions, ¯ X n ! p μ . 3/20
LLN I Let X 1 , . . . , X n be a sample of independent identically distributed (iid) random variables. Let EX i = μ . If Var ( X i ) = σ 2 < then ¯ X n !

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

## This note was uploaded on 03/24/2012 for the course ECON 326 taught by Professor Whisler during the Spring '10 term at UBC.

### Page1 / 21

Lecture 16 Large sample results (Consistency) - Economics...

This preview shows document pages 1 - 6. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online