Hi,
For an ordered probit or logit model, is there any way to save
marginal effect estimates produced via the suite of spost commands?
For example:
oprobit Y X1
prvalue, x(X1=0) save delta
praccum , using(Xmat) xis(0)
prvalue, x(X1=1) dif delta
* this produces nice marginal effect estimates (ie. changes in the
PR(Y=1|X1=0) - PR(Y=1|X1=1)) including CI intervals.
oprobit: Change in Predictions for Y
Confidence intervals by delta method
Current Saved Change 95% CI for Change
Pr(y=1x): 0.1820 0.3547 -0.1727 [-0.2140, -0.1314]
Pr(y=2x): 0.2161 0.2544 -0.0383 [-0.0384, -0.0381]
Pr(y=3x): 0.2583 0.2168 0.0415 [ 0.0331, 0.0500]
* now I try to save them using:
praccum , using(Xmat) xis(1) gen(Xpred)
But praccum does not save these marginal effects and its CIs, just the
predicted probabilities for each category. The same is true for prgen
the other command that would allow me to save estimates. I love spost
and really like to use it here, but my key quantity of interest are
the marginal effects and in particular their CIs so it would be very
helpful if I could save them somehow (to produce plots, tables, etc.).
Is there any way to do this? Is spost can't do this, is there any
other way to generate and store these?
Thank you very much.
Best,
Tom
*
* 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/
