Econometrics-I-6

Econometrics-I-6 - Applied Econometrics William Greene...

This preview shows pages 1–9. Sign up to view the full content.

Applied Econometrics William Greene Department of Economics Stern School of Business

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

View Full Document
Applied Econometrics 6. Finite Sample Properties of the Least Squares Estimator
Terms of Art Estimates and estimators Properties of an estimator - the sampling  distribution “Finite sample” properties as opposed to  “asymptotic” or “large sample” properties

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

View Full Document
The Statistical Context of Least Squares Estimation The sample of data from the population The stochastic specification of the regression  model Endowment of the stochastic properties of the  model upon the least squares estimator
Least Squares - - - - - = - = - = = = + = + ε + ε + ε 1 1 1 n 1 1 i i i 1 n 1 i i i 1 n 1 i i i 1 n i i i 1 ( )    = ( ) ( ) Also ( ) = ( ) y    ( )    = ( )    =    (Influence functions) b X'X X'y X'X X'(X + ) = X'X X' b X'X X'y X'X x = X'X x X'X x v β ε β ε β β β

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

View Full Document
Deriving the Properties So,  b  = a parameter vector + a linear combination  of the disturbances, each times a vector. Therefore,  b  is a vector of random variables.  We  analyze it as such.      The assumption of nonstochastic regressors.   How it is used at this point. We do the analysis conditional on an  X , then show  that results do not depend on the particular  in  hand, so the result must be general – i.e.,  independent of  X
Properties of the LS Estimator Expected value and the property of unbiasedness.  E[ b|X ] =  β  = E[ b ].   Prove this result. A Crucial Result About Specification:      y   =   X 1 β 1  +  X 2 β 2  +  ε Two sets of variables.  What if the regression is  computed without the second set of variables? What is the expectation of the "short" regression  estimator?       b 1   =  ( X 1 X 1 ) -1 X 1 y

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

View Full Document
The Left Out Variable Formula (This is a VVIR!)       E[ b 1 ]  =   β 1   +  ( X 1 X 1 ) -1 X 1 X 2 β 2 The (truly) short regression estimator is biased. Application:
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 11/23/2011 for the course ECON B30.3351 taught by Professor Professorw.greene during the Spring '10 term at NYU.

Page1 / 21

Econometrics-I-6 - Applied Econometrics William Greene...

This preview shows document pages 1 - 9. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online