EC2SLS is a random-effect estimator based on the assumption that the
individual effect is not correlated with any of the regressors.
- xtivreg, fe- implements the "within" or "fixed-effect" estimator,
which allows the individual effect to be correlated with the regressors.
As explained in the doc for -xtivreg-, EC2SLS can be expressed as a
weighted average of the "within" and "between" estimators.
Jean Salvati
> -----Original Message-----
> From: [email protected]
> [mailto:[email protected]] On Behalf Of
> bulent Koksal
> Sent: Wednesday, December 15, 2004 4:27 PM
> To: [email protected]
> Subject: st: A question about xtivreg
>
> A question about xtivreg
>
> What is the difference between Fixed effect below and ec2sls
> estimator? As I know EC2sls is used to estimate simulatenous
> equation panel data models. So if I can use 1) and have
> endogoneous right hand side variables, why do I need EC2sls?
> Thank you for any replies.
>
> 1)
> Fixed-effects model
>
> xtivreg depvar [ varlist_1 ] (varlist_2 = varlist_iv) [if exp]
> [in range] , fe [ regress i(varname) small first level
> (#) ]
>
> and
>
>
> 2)
> GLS Random-effects model
>
> xtivreg depvar [ varlist_1 ] (varlist_2 = varlist_iv) [if exp]
> [in range] [, re ec2sls nosa regress
> i(varname) theta small
> first level(#) ]
>
>
> *
> * For searches and help try:
> * http://www.stata.com/support/faqs/res/findit.html
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
>
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
