Bookmark and Share

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]

st: xtivreg2 or new Stata12 command sem?


From   "Dithmer, Jan" <jdithme@food-econ.uni-kiel.de>
To   "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Subject   st: xtivreg2 or new Stata12 command sem?
Date   Mon, 23 Jan 2012 15:23:27 +0100

Dear Statalisters,

I want to estimate a system of equations with panel data, where there are several interrelationships between the variables.
I estimated the first equation (1) with GMM using xtabond2, treating variable B as endogenous. However, I fear that I might lose
some potential indirect effects that B has on some explanatory variables in (1). I would use the sureg command, but it does not support panel data. My intuition tells me that, when B positively influences D and E, and they themselves have a positive coefficient in (1), the effect of B on Y in (1) should be greater than I have estimated, or I am wrong here?

(1) Y_it = a + bY_it-1 + cB_it + dC_it + eD_it + fE_it + error

(2) B_it = gY_it + hC_it + iF_it + error

(3) D_it = jB_it + kG_it+lH_it +error

(4) E_it = mB_it + nJ_it + error  

So, my question is: how can I estimate the whole system of equations to capture all indirect effects? Might this be a task for the Structural equation modeling "sem" command in Stata12 (which I not have)
Or should I just estimate the equations separately using xtabond2 for the first and xtivreg2 for the rest? But then I already have the result of the first equation, in which I am mainly interested in...

Thanks for any suggestions!

Best, Jan

*
*   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 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index