Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: RE: ivprobit is adding extra instruments


From   "Wooldridge, Jeffrey" <[email protected]>
To   <[email protected]>
Subject   st: RE: ivprobit is adding extra instruments
Date   Wed, 9 Mar 2011 10:30:42 -0500

I believe this is just semantics. Each exogenous variable acts as its own instrument and so all exogenous variables -- whether in the model or excluded -- a labeled as instruments. Plus, remember that the reduced form for the consumption variable includes all exogenous variables. It's true that those omitted from the probit equation are often called "the instruments for consumption," but this convention is not universal.

So I think it's doing what you want. I suggestion to you is to rescale the cons_pcm variable. If it is in dollars I would use something like thousands, or even millions, of dollars. Then the coefficient would be much easier to read. If cons_pcm is always strictly positive, you might try log(cons_pcm) instead and see if it improves the log likelihood.

Jeff

-----Original Message-----
From: [email protected] [mailto:[email protected]] On Behalf Of Sarah Alkenbrack
Sent: Wednesday, March 09, 2011 10:21 AM
To: [email protected]
Subject: st: ivprobit is adding extra instruments

Hi Stata users,

I am running -ivprobit- to look at the determinants of enrolment in
health insurance (cbhi). I have several exogenous regressors and one
endogenous regressor (consumption).
I am using wealthindex as an intrumental variable for consumption.
However, when I run the ivprobit model all my exogenous regressors
appear in the "instruments" list. Could someone please
tell me how to prevent this from happening? I am copying the stata
code and results below. I noticed in the archives that others have had
this problem but so far, I have not seen any answers
posted on what might be causing this problem or how to correct it.

Thank you in advance for your help.

Sarah

. # delimit;
delimiter now ;
. ivprobit cbhi age_hhead age2 edu_hh2 edu_hh3 edu_hh4 edu_hh5 mar_hh
hhmem_cat2 hhmem_cat3
> hhhealth_poor hh_chronic hh_diffic risk pregnancy wra any_oldmem j_hh2 j_hh3 j_hh4
> hlthseek_mod campaign qual_percep urban door_to_door chief_mem
> pharm_in_vil drugsel_in_vil hlthcent_in_vil privclin_in_vil young edu_chief num_camp_vill home_collection
> qual2 qual3 size_ln name_hosp1 name_hosp3 name_hosp4 name_hosp5 name_hosp6 (cons_pcm=wealthindex) ;

Fitting exogenous probit model

Iteration 0:   log likelihood = -1909.5425
Iteration 1:   log likelihood =  -1687.946
Iteration 2:   log likelihood = -1681.6413
Iteration 3:   log likelihood = -1681.6142
Iteration 4:   log likelihood = -1681.6142

Fitting full model

Iteration 0:   log likelihood = -42769.776
Iteration 1:   log likelihood = -42766.676
Iteration 2:   log likelihood = -42736.028
Iteration 3:   log likelihood = -42734.629
Iteration 4:   log likelihood = -42734.269
Iteration 5:   log likelihood = -42734.266
Iteration 6:   log likelihood = -42734.266

Probit model with endogenous regressors           Number of obs   =       3000

                    Wald chi2(42)   =    1113.82
Log likelihood = -42734.266                       Prob > chi2     =     0.0000

------------------------------------------------------------------------------
             |      Coef.   Std. Err.      z    P>|z|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
    cons_pcm |   3.59e-06   2.15e-07    16.68   0.000     3.17e-06    4.01e-06
   age_hhead |   .0320042   .0129973     2.46   0.014       .00653    .0574784
        age2 |  -.0001774   .0001228    -1.45   0.148    -.0004181    .0000632
     edu_hh2 |    .051426   .0879334     0.58   0.559    -.1209203    .2237723
     edu_hh3 |  -.0075595   .1023748    -0.07   0.941    -.2082106    .1930915
     edu_hh4 |   -.000683   .1285689    -0.01   0.996    -.2526735    .2513075
     edu_hh5 |  -.2986249   .1713749    -1.74   0.081    -.6345136    .0372638
      mar_hh |  -.0539035    .067056    -0.80   0.421    -.1853308    .0775237
  hhmem_cat2 |   .4222092   .0675468     6.25   0.000     .2898198    .5545985
  hhmem_cat3 |   .7099401   .0822271     8.63   0.000     .5487778    .8711023
hhhealth_p~r |   .1550617   .0699122     2.22   0.027     .0180362    .2920872
  hh_chronic |    .159681   .0718297     2.22   0.026     .0188973    .3004647
   hh_diffic |   .2613713   .0741209     3.53   0.000      .116097    .4066456
        risk |  -.0482252   .0467953    -1.03   0.303    -.1399423    .0434919
   pregnancy |   .1200344   .1214774     0.99   0.323    -.1180569    .3581257
         wra |   .1033809   .0289192     3.57   0.000     .0467004    .1600614
  any_oldmem |   .0792428   .0680778     1.16   0.244    -.0541872    .2126729
       j_hh2 |   .0512404   .0815692     0.63   0.530    -.1086323     .211113
       j_hh3 |   -.349126   .0806268    -4.33   0.000    -.5071516   -.1911004
       j_hh4 |   .1928496   .0843208     2.29   0.022     .0275838    .3581154
hlthseek_mod |  -.0359996   .0969011    -0.37   0.710    -.2259223     .153923
    campaign |   .5068671   .0781293     6.49   0.000     .3537365    .6599977
 qual_percep |   .1840314   .0514758     3.58   0.000     .0831408    .2849221
       urban |  -.0999875   .0590944    -1.69   0.091    -.2158103    .0158353
door_to_door |   .0564977   .0719369     0.79   0.432     -.084496    .1974914
   chief_mem |   .0811248   .0599964     1.35   0.176     -.036466    .1987156
pharm_in_vil |   .0269211   .0582651     0.46   0.644    -.0872763    .1411185
drugsel_in~l |   .0693485   .0586169     1.18   0.237    -.0455385    .1842355
hlthcent_i~l |   .0089279   .0823509     0.11   0.914    -.1524769    .1703327
privclin_i~l |  -.0547559   .0857815    -0.64   0.523    -.2228846    .1133728
       young |   .0899074   .0715818     1.26   0.209    -.0503903    .2302051
   edu_chief |  -.0888131   .0528856    -1.68   0.093    -.1924671    .0148408
num_camp_v~l |   .0655667   .0548026     1.20   0.232    -.0418444    .1729779
home_colle~n |   .1944581   .0606159     3.21   0.001     .0756531    .3132631
       qual2 |  -.1778623   .0896638    -1.98   0.047    -.3536001   -.0021245
       qual3 |  -.2049839   .1081036    -1.90   0.058     -.416863    .0068952
     size_ln |  -.0059746    .042326    -0.14   0.888    -.0889321    .0769829
  name_hosp1 |   .1476783   .1168295     1.26   0.206    -.0813032    .3766598
  name_hosp3 |    .536909   .1350044     3.98   0.000     .2723053    .8015128
  name_hosp4 |   .4347936   .1069197     4.07   0.000     .2252348    .6443523
  name_hosp5 |    .228802   .1274495     1.80   0.073    -.0209945    .4785985
  name_hosp6 |   .9189969   .1301651     7.06   0.000     .6638779    1.174116
       _cons |   -4.82205   .4438201   -10.86   0.000    -5.691922   -3.952179
-------------+----------------------------------------------------------------
     /athrho |  -.8556093   .0998439    -8.57   0.000      -1.0513   -.6599188
    /lnsigma |   12.27712     .01291   950.98   0.000     12.25181    12.30242
-------------+----------------------------------------------------------------
         rho |  -.6939885   .0517571                     -.7823111   -.5783094
       sigma |   214725.5   2772.097                      209360.5    220228.1
------------------------------------------------------------------------------
Instrumented:  cons_pcm
Instruments:   age_hhead age2 edu_hh2 edu_hh3 edu_hh4 edu_hh5 mar_hh
               hhmem_cat2 hhmem_cat3 hhhealth_poor hh_chronic hh_diffic risk
               pregnancy wra any_oldmem j_hh2 j_hh3 j_hh4 hlthseek_mod
               campaign qual_percep urban door_to_door chief_mem
               pharm_in_vil drugsel_in_vil hlthcent_in_vil privclin_in_vil
               young edu_chief num_camp_vill home_collection qual2 qual3
               size_ln name_hosp1 name_hosp3 name_hosp4 name_hosp5
               name_hosp6 wealthindex
------------------------------------------------------------------------------
Wald test of exogeneity (/athrho = 0): chi2(1) =    73.44 Prob > chi2 = 0.0000

*
*   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/

*
*   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/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index