0
$\begingroup$

Is it possible to utilise the system GMM estimator using xtabond2 when our dependent variable lies within the interval [0, 1]. Moreover, the mass point is at around 0.

Thank you,

Sagnik

$\endgroup$
2
$\begingroup$

GMM does not impose distrubutional assumptions on the errors, so you can estimate the model and the standard errors; interpreting the model for testing and inference might be tricky.

$\endgroup$
0
$\begingroup$

There is no such restriction on dependent variable to apply GMM. You can apply GMM even if dependent variable is binary.

For more detail you can refer:

System Equation by Instrumental Variable, Chapter 8, Econometric Analysis of Cross Section and Panel Data by Wooldridge, 2010

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.