st: Re: How to deal with missing standard error for ivprobit

[xueliansharon <xuelianstata@gmail.com>]

Dear all,

The following is the command I used:

ivprobit y x1 x2 (z1 z2 z3 z4 z5= I1 I2 I3 I4 I5 I6 I7 I8 I9 I10), tech(dfp)
nrtol(1e-5) showtolerance

Here, y is the dependent variable, x1 and x2 are exogenous variables, z1-z5
are five endogenous variables (each of them is standardized to have mean 0,
variance 1), I1-I10 are instruments, but all of the instruments (I1-I10) are
dummy variables. 

Then I got the results like:


------------------------------------------------------------------------------
             |      Coef.   Std. Err.      z    P>|z|     [95% Conf.
Interval]
-------------+----------------------------------------------------------------
Y     |
   z1 |   .4000544   .1430333     2.80   0.005     .1197143    .6803945
   z2 |  -.0470843   .2059814    -0.23   0.819    -.4508004    .3566317
   z3 |   .3759035   .1411249     2.66   0.008     .0993037    .6525032
   z4 |  -.4955611          .        .       .            .           .
   z5 |   -1.05645    .128653    -8.21   0.000    -1.308606   -.8042952

Please note that the standard error for z4 is missing. 
What's more confusing is that when I ask to show the first-stage results,
the standard errors for I1 and I2 in the equation of z1 (here, I mean the
first-stage equation with z1 as the dependent variable) are also missing. 

I really can't understand why such things happen. Can anybody tell me how to
deal with such missing standard errors? 

Any help would be greatly appreciated.

Sharon


--
View this message in context: http://statalist.1588530.n2.nabble.com/How-to-deal-with-missing-standard-error-for-ivprobit-tp6176824p6182640.html
Sent from the Statalist mailing list archive at Nabble.com.
*
*   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/