Instrumental variable analysis: evaluate the strength of instrumental variable in "ivprobit" syntax

[Grace Wan]

Hello, I've done an instrumental variable analysis using "ivprobit", because the dependent variable in my research is coded in 0 and 1.
I wonder how to interpret the strength of IV that I used in the equation

Here is my procedure below:

 ivprobit Heart_disease Height (Weight=rs578776_genotype), twostep first
Checking reduced-form model...
first-stage regression

      Source |       SS           df       MS      Number of obs   =     3,509
-------------+----------------------------------   F(2, 3506)      =   1071.14
       Model |  213791.893         2  106895.947   Prob > F        =    0.0000
    Residual |  349887.519     3,506  99.7967823   R-squared       =    0.3793
-------------+----------------------------------   Adj R-squared   =    0.3789
       Total |  563679.412     3,508  160.683983   Root MSE        =    9.9898

-----------------------------------------------------------------------------------
           Weight |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]
------------------+----------------------------------------------------------------
rs578776_genotype |   .3987121   .2926412     1.36   0.173    -.1750522    .9724765
           Height |   .9997172   .0216051    46.27   0.000     .9573573    1.042077
            _cons |  -99.16142   3.661257   -27.08   0.000    -106.3398   -91.98301
-----------------------------------------------------------------------------------

Two-step probit with endogenous regressors        Number of obs   =      3,509
                                                  Wald chi2(2)    =       2.84
                                                  Prob > chi2     =     0.2414

------------------------------------------------------------------------------
             |      Coef.   Std. Err.      z    P>|z|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
      Weight |   .2141107   .2000621     1.07   0.285    -.1780039    .6062253
      Height |  -.2218302   .2000962    -1.11   0.268    -.6140115    .1703511
       _cons |   20.92252   19.74899     1.06   0.289    -17.78478    59.62983
------------------------------------------------------------------------------
Instrumented:  Weight
Instruments:   Height rs578776_genotype
------------------------------------------------------------------------------
Wald test of exogeneity: chi2(1) = 2.03                   Prob > chi2 = 0.1538

Does the F=1071.14 represents the strength of instrumental variable, which is the same when we use "ivregress" to obtain the result?
In addition, does the adjusted R-square=0.3793 represents the multiple determination coefficient between IV and X?
Or does it have the other statistics about the strength of instrumental vaiable in "ivprobit" syntax

Thank you for your answer in advance!!!

[Festus odingo]

In ivprobit the reduced form for the endogenous explanatory variable is linear, so you can use the same diagnostics as in the ivreg2. or you can estimate using ivreg2 model ! likewise you can comment on the F - stat. To the best of my knowledge no such study on an F statistic in case where we have a non linear structural model like yours.read more on stock-yogo ! cheers

[Grace Wan]

Festus:
I've installed the "ivreg2" command, and it really works.

Here's the result I used this command below:

ivreg2 Heart_disease Height (Weight=rs578776_genotype)

IV (2SLS) estimation
--------------------

Estimates efficient for homoskedasticity only
Statistics consistent for homoskedasticity only

                                                      Number of obs =     3509
                                                      F(  2,  3506) =     1.34
                                                      Prob > F      =   0.2613
Total (centered) SS     =  231.3308635                Centered R2   =  -1.1843
Total (uncentered) SS   =          249                Uncentered R2 =  -1.0293
Residual SS             =  505.2866901                Root MSE      =    .3795

------------------------------------------------------------------------------
Heart_dise~e |      Coef.   Std. Err.      z    P>|z|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
      Weight |   .0305102   .0278801     1.09   0.274    -.0241339    .0851543
      Height |  -.0314976   .0278792    -1.13   0.259    -.0861397    .0231446
       _cons |     3.2464    2.75135     1.18   0.238    -2.146148    8.638947
------------------------------------------------------------------------------
Underidentification test (Anderson canon. corr. LM statistic):           1.857
                                                   Chi-sq(1) P-val =    0.1730
------------------------------------------------------------------------------
Weak identification test (Cragg-Donald Wald F statistic):                1.856
Stock-Yogo weak ID test critical values: 10% maximal IV size             16.38
                                         15% maximal IV size              8.96
                                         20% maximal IV size              6.66
                                         25% maximal IV size              5.53
Source: Stock-Yogo (2005).  Reproduced by permission.
------------------------------------------------------------------------------
Sargan statistic (overidentification test of all instruments):           0.000
                                                 (equation exactly identified)
------------------------------------------------------------------------------
Instrumented:         Weight
Included instruments: Height
Excluded instruments: rs578776_genotype
------------------------------------------------------------------------------

Surely, it has Cragg-Donald Wald F statistic, does the result "1.856" means that the instrumental variable I used is weak?
Moreover, the Sargan statistic below is "0.000", does it means that it has overidentification?
Thus, the IV I chose in this analysis may not be a suitable one?

Thank you for your help.

[Grace Wan]

I also have a question.

If I want to do an endogeneous test (eg. Durbin-Wu-Hausman test, or the test similar to this)
Can I get the statistic in this syntax?

Thanks a lot!!!

[Wesley Hon]

Hi,Wan:
How do you cope with this question?I have the same question while writting my thesis.
Can u help me with that?
Thanks a lot!!!

[Wesley Hon]

I also have a question.

If I want to do an endogeneous test (eg. Durbin-Wu-Hausman test, or the test similar to this)
Can I get the statistic in this syntax?

Thanks a lot!!!

I finally figured it out,thanks anyway!

[Grace Wan]

I finally figured it out,thanks anyway!

Hello Wesley, sorry for the late reply
I'm majoring in Epidemiology, and I use instrumental variable in my thesis

[Parul Gupta]

Wesley Hon Could you please share your solution? I am having a hard time interpreting the results from ivprobit.