# st: estimating standard errors for interaction terms in xttobit

 From "Monica Fisher" To statalist@hsphsun2.harvard.edu Subject st: estimating standard errors for interaction terms in xttobit Date Sat, 18 Aug 2007 18:47:25 -0400

Dear Statalisters,

I have a model with several interaction terms such as this:

y = a0 + a1x1 + a2x2 + a3x3 + a4(x1*x2) + a5(x1*x3)

I have panel data and y is censored at zero, so I'm using xttobit and mfx compute to estimate the model and obtain marginal effects. I.e.:

. xttobit y x1 x2 x3 interx1x2 interx1x3

. mfx compute, predict(e(0,.))

Using results from mfx, I can easily calculate the marginal effect of x1 on y (dy/dx1). What I'm wondering is if anyone knows how to calculate the standard error of dy/dx1 in Stata? I have seen early postings on how to do this for cross-sectional tobit, but am unable to use the same set of commands for xttobit. Ideas?

Thanks!

Monica

_________________________________________________________________
Puzzles, trivia teasers, word scrambles and more. Play for your chance to win! http://club.live.com/home.aspx?icid=CLUB_hotmailtextlink

*
* 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/