st: -esttab- after margins

["Haiyong Xu" <hxu@mednet.ucla.edu>]

Hi there,
I ran two -margins- commands after a logit model. The output looks like 
this.
. margins res_any_pd

Predictive margins                                Number of obs   = 
14330
Model VCE    : Linearized

Expression   : Pr(w2_pred_obese), predict()

------------------------------------------------------------------------------
            |            Delta-method
            |     Margin   Std. Err.      z    P>|z|     [95% Conf. 
Interval]
-------------+----------------------------------------------------------------
 res_any_pd |
         0  |   .3051124   .0054582    55.90   0.000     .2944145 
.3158102
         1  |   .3306719   .0167294    19.77   0.000     .2978829 
.3634608
------------------------------------------------------------------------------

. margins, dydx(res_any_pd)

Average marginal effects                          Number of obs   = 
14330
Model VCE    : Linearized

Expression   : Pr(w2_pred_obese), predict()
dy/dx w.r.t. : 1.res_any_pd

------------------------------------------------------------------------------
            |            Delta-method
            |      dy/dx   Std. Err.      z    P>|z|     [95% Conf. 
Interval]
-------------+----------------------------------------------------------------
1.res_any_pd |   .0255595   .0174061     1.47   0.142    -.0085558 
.0596747
------------------------------------------------------------------------------
Note: dy/dx for factor levels is the discrete change from the base level.

I am thinking of using -exttab- or -extout- to print a table like this.

res_any_pd 0: .3051124
res_any_pd 1: .0255595 (-.0085558, .0596747)

So, I only want to print out the point estimate of res_any_pd at zero and 
the difference between one and zero with its CI. I tried -estpost- 
and -estadd- but got some error because the two -margins- output the same 
matrices. Could someone give me some suggestions?
Thank you very much!
Haiyong


*
*   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/