Processing math: 100%

MathType

Tuesday, 21 June 2016

Pooled or Population-Average Estimators with Stata (Panel)




Pooled estimator simply regress yit on an intercept and xit using both between (cross-section) and within (time-series) variation in the data.

Pooled or population-average estimator are consistent if the RE model is appropriate and are inconsistent if the FE model is appropriate.

From discussion in within and between variation,  the individual-spesific-effects model for the scalar dependent variable yit specifies that;

yit=αi+{x}'itβ+εit                                                            (1)

where {x}'it are regressor, αi are random individual-spesific-effects, and εit is and idiosyncratic error

Pooled OLS estimator can be motivated from the individual-effects model by rewriting Eq (1) as the pooled model.

lwage=α+β1expit+β2exp2it+β3wksit+β4edit+(αiα+uit)                                (2)


Consistency of OLS requires that the error term (αiα+uit) be uncorrelated with independent variables.

So pooled OLS is consistent in the in the RE model but inconsistent in the FE model because then αi  is correlated with independent variables.

The pooled estimator, or PA estimator is obtained by using the xtreg command with the pa option.

The option is corr( ) for place different restriction on the error correlation, and vce(robust) to obtain cluster-robust standard errors.

We use the data Paneldata01.

xtset id t


Assumed that there are AR(2) error process in model Eq(2), to estimate PA,

xtreg lwage exp exp2 wks ed, pa corr(2) vce(robust)







 











No comments:

Post a Comment