st: wald test when I use GMM method in stata 11

[Song Nhac <songnhac@gmail.com>]

Dear Statalist,

I have a problem after doing GMM in Stata11- I would like to do a wald
test for 2 coefficient but it reports an error. Please see following:

gmm (y :y - {c0} - {c1}*a - {c2}*b - {c3}*aXb ),  instruments (a b
aXb) winitial(unadjusted, independent)

Step 1
Iteration 0:   GMM criterion Q(b) =  .00560077
Iteration 1:   GMM criterion Q(b) =  2.232e-25
Iteration 2:   GMM criterion Q(b) =  1.627e-34

Step 2
Iteration 0:   GMM criterion Q(b) =  4.855e-32
Iteration 1:   GMM criterion Q(b) =  4.855e-32

GMM estimation

Number of parameters =   4
Number of moments    =   4
Initial weight matrix: Unadjusted                     Number of obs  =    2196
GMM weight matrix:     Robust

------------------------------------------------------------------------------
             |               Robust
             |      Coef.   Std. Err.      z    P>|z|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
         /c0 |   .2230482   .0168333    13.25   0.000     .1900556    .2560408
         /c1 |  -.0102612   .0011147    -9.21   0.000    -.0124459   -.0080765
         /c2 |  -.1681484   .0220192    -7.64   0.000    -.2113053   -.1249916
         /c3 |   .0092258   .0014946     6.17   0.000     .0062964    .0121551
------------------------------------------------------------------------------
Instruments for equation 1: a b aXb _cons

test b + aXb = 0
regressor b not found
r(111);

I tried it many times, but it alway says that regressor b not found. I
don't know what happens in this since I am not expert in STATA.

Many thanks for your kind attention.

Song Nhac
*
*   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/