Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: RE: should I concern the endogeneity problem


From   "Benjamin Villena Roldan" <bvillena@troi.cc.rochester.edu>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: RE: should I concern the endogeneity problem
Date   Mon, 29 Sep 2008 15:34:39 -0400

A simple OLS estimation provide expected marginal ceteris paribus effects, i.e. expected partial derivatives of the dependent variable wrt a regressor. You don't need the regressors to be mutually independent, just that regressors are independent from your error term (you may need something even weaker, E(xu)=0). I think any basic econometrics textbook can offer a discussion about this point.
However, without further information it is difficult to be sure that your theoretical statements actually fit your data.

Benjamin


-----Mensaje original-----
De: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] En nombre de Gordon
Enviado el: Monday, September 29, 2008 2:29 PM
Para: statalist@hsphsun2.harvard.edu
Asunto: st: should I concern the endogeneity problem

Hi,

I am estimating a model:

Y = X1 + X2 + X1*X2

I am confident that X1 and X2 are exogenous to Y, however it is likely
that X1 is influenced by X2. In this case, should I worry about any
endogeneity?

Thanks for your insights!

Gordon
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index