Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: xtabond2 & Margins
From
Christopher Baum <[email protected]>
To
"[email protected]" <[email protected]>
Subject
Re: st: xtabond2 & Margins
Date
Sun, 2 Feb 2014 12:57:43 +0000
<>
On Feb 2, 2014, at 2:33 AM, Stevenwrote:
> I have: xtabond2 lnenergycap l(1/2).lnenergycap lngdpcap , ///
> gmm(l(1).lnenergycap , laglimits(1 12) collapse ) ///
> gmm(lngdpcap, laglimits(2 12) collapse) ///
> iv(l(2).lnenergycap) ///
> robust twostep small ar(2)-
>
> If I use -margins, dydx(*) atmeans nose-, the results are just
> spitting me back the coefficients. How do I ensure the results take
> into account the lagged dependent variables on the right hand side?
Well, xtabond2 (SSC) estimates the dynamic panel data (DPD) model, which is a linear regression, so the dydx are
indeed just the estimated coefficients. Were you hoping to compute the long-run or steady-state effects of the regressors?
That you can do with -nlcom-. Here is a simple example using time-series regression:
webuse lutkepohl,clear
reg linvestment L.linvestment lincome
margins, dydx(*)
nlcom _b[lincome] / (1-_b[L.linvestment])
This will compute the long-run multiplier for income (assuming stability conditions are satisfied).
KIt
Kit Baum
Professor of Economics and Social Work, Boston College, Chestnut Hill MA, USA
DIW Research Professor, Department of Macroeconomics, DIW Berlin, Berlin, Germany
[email protected] | http://ideas.repec.org/e/pba1.html
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/