st: heckprob mfx

["Jiang, Lan" <Lan.Jiang@va.gov>]

Hi experts,
�
I am new in stata and even newer in statalist.� I am having a heckprob problem for your help.  As below, I have hospital (dummy var) insignificant in the 2nd step modeling insignificant, but when I use mfx to calculate the marginal effects, it becomes significant.� Here is some of the output.
�
Your advices will be highly appreciated.
�
Thanks!
�
Lan
�
heckprob v29424� hospital mh othorg numclient_100 svc_breadth invol_10pct, sel(v29422=hospital mh othorg sanicotine_10pct svc_breadth phyimp) nolog
�
Probit model with sample selection������������� Number of obs����� =������ 494
� ����������������������������������������������Censored obs������ =������ 254
����������������������������������������������� Uncensored obs���� =������ 240
�
����������������������������������������������� Wald chi2(6)������ =���� 18.75
Log likelihood = -452.8194��������������������� Prob > chi2������� =��� 0.0046
�
------------------------------------------------------------------------------
������������ |����� Coef.�� Std. Err.����� z��� P>|z|���� [95% Conf. Interval]
-------------+----------------------------------------------------------------
v29424������ |
��� hospital |�� .6798989�� .3715279���� 1.83�� 0.067��� -.0482823���� 1.40808
��������� mh |�� .2269317�� .3036784���� 0.75�� 0.455��� -.3682671��� .8221305
����� othorg |� -.0007292�� .2278594��� -0.00�� 0.997��� -.4473254��� .4458669
numclien~100 |�� .0235725��� .010234���� 2.30�� 0.021���� .0035143��� .0436308
�svc_breadth |��� .052458�� .0230032���� 2.28�� 0.023���� .0073725��� .0975435
�invol_10pct |� -.0561788��� .025818��� -2.18�� 0.030��� -.1067811�� -.0055764
������ _cons |� -1.420717��� .874694��� -1.62�� 0.104��� -3.135086��� .2936517
-------------+----------------------------------------------------------------
v29422������ |
��� hospital |�� .5296687�� .2100133���� 2.52�� 0.012���� .1180503��� .9412872
��������� mh |� -.0741861�� .1824389��� -0.41�� 0.684��� -.4317597��� .2833876
����� othorg |� -.1386789�� .1368669��� -1.01�� 0.311��� -.4069331��� .1295752
sanicotine~t |�� .0505129�� .0209759���� 2.41�� 0.016����� .009401��� .0916248
�svc_breadth |�� .0342173��� .009774���� 3.50�� 0.000���� .0150606��� .0533739
����� phyimp |� -.0611262�� .0253105��� -2.42�� 0.016��� -.1107339�� -.0115186
������ _cons |� -.5084769�� .2220102��� -2.29�� 0.022���� -.943609�� -.0733449
-------------+----------------------------------------------------------------
���� /athrho |�� .0993535�� .8370807���� 0.12�� 0.906��� -1.541294��� 1.740001
-------------+----------------------------------------------------------------
�������� rho |�� .0990279�� .8288718� �������������������-.9123376��� .9402268
------------------------------------------------------------------------------
LR test of indep. eqns. (rho = 0):�� chi2(1) =���� 0.01�� Prob > chi2 = 0.9047
------------------------------------------------------------------------------
�
�
mfx compute, eqlist(v29424) predict(pcond) at (hospital=1, svc_breadth=12.6, numclient_100=7.1, invol_pct=3.9)
�
Marginal effects after heckprob
����� y� = Pr(v29424=1|v29422=1) (predict, pcond)
�������� =� .48923093
------------------------------------------------------------------------------
variable |����� dy/dx��� Std. Err.���� z��� P>|z|� [��� 95% C.I.�� ]����� X
---------+--------------------------------------------------------------------
hospital*|�� .2403324����� .10073��� 2.39�� 0.017�� .042913 �.437752�������� 1
����� mh*|�� .0919905����� .11726��� 0.78�� 0.433� -.137838� .321819�� .143725
� othorg*|�� .0026067����� .08942��� 0.03�� 0.977� -.172645� .177859�� .425101
numc~100 |�� .0090431����� .00395��� 2.29�� 0.022�� .001307� .016779������ 7.1
svc_br~h |�� .0201245����� .00859��� 2.34�� 0.019�� .003293� .036956����� 12.6
inv~0pct |� -.0215519����� .00987�� -2.18�� 0.029� -.040897 -.002207��� 3.5481
------------------------------------------------------------------------------
(*) dy/dx is for discrete change of dummy variable from 0 to 1

*
*   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/