F-test after xtivreg

[Maye Ehab]

Dear Statalisters,

I am running an instrumental variable model using the following codes. I am trying to check the exogeneity of the instrument, whether it is a strong or a weak one.

global X2 "c.age##c.age i.educ4 i.marital3 hhsize urban public"
xtivreg Y $X1 (endvar= $IV), re vce(robust) first
xtoverid

However, the

xtoverid

did not work and it gave me the below error:

cage#c: operator invalid
r(198);

I have also tried the below code and it gave me an error term that endog is not allowed.

xtivreg Y $X1 (endvar= $IV), fe first endog(endvar)

Could you please advise me on this?

Best regards,
Maye

[Carlo Lazzaro]

Maye:
the user-written programme -xtoverid- does not support -fvvarlist- notation.
Hence, you should create interactions by hand and prefix your code with -xi-.

[Maye Ehab]

Dear Carlos,

Thank you for your reply.

It worked but did not give me the statistic:
The code:

global X2 "age agesq basiceducation secondaryeducation postsecondary married widowedordivorced hhsize urban public"
xi: xtivreg Y $X2 (endogvar= $IV), re vce(robust) first

The result:

Test of overidentifying restrictions:
Cross-section time-series model: xtivreg g2sls  robust cluster(Findid)
Sargan-Hansen statistic   0.000  (equation exactly identified)

Can you please guide me what went wrong?
I was not able to find a reference with enough examples for this command. If you can provide me with one, I would be grateful.

Best regards,
Maye

[Maye Ehab]

I actually found another option that gave me the tests I need

 
 xtoverid,noi

Thank you again for clarifying to me why the -xtoverid- did not work in the first place.

[Carlo Lazzaro]

Maye:
please note that -xtivreg, re- (just like -xtreg, re-) does not give you back an F-test but a chi2 one:

webuse nlswork
xtivreg ln_w age c.age#c.age not_smsa (tenure = union south), vce(robust) first

First-stage G2SLS regression
                                                 Number of obs    =     19,007
                                                 Wald chi(5)      =       4932
                                                 Prob > chi2      =     0.0000

------------------------------------------------------------------------------
             |               Robust
      tenure |      Coef.   Std. Err.      z    P>|z|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
         age |   .1357715   .0382906     3.55   0.000     .0607233    .2108196
             |
 c.age#c.age |   .0021357   .0006504     3.28   0.001      .000861    .0034105
             |
    not_smsa |  -.0178559    .068881    -0.26   0.795    -.1528601    .1171484
       union |   1.032321   .0650498    15.87   0.000     .9048261    1.159816
       south |  -.1311183   .0637709    -2.06   0.040     -.256107   -.0061297
       _cons |   -3.02552   .5449259    -5.55   0.000    -4.093555   -1.957485
------------------------------------------------------------------------------

G2SLS random-effects IV regression              Number of obs     =     19,007
Group variable: idcode                          Number of groups  =      4,134

R-sq:                                           Obs per group:
     within  = 0.0620                                         min =          1
     between = 0.1745                                         avg =        4.6
     overall = 0.1206                                         max =         12


                                                Wald chi2(4)      =     403.60
corr(u_i, X)       = 0 (assumed)                Prob > chi2       =     0.0000

                             (Std. Err. adjusted for 4,134 clusters in idcode)
------------------------------------------------------------------------------
             |               Robust
     ln_wage |      Coef.   Std. Err.      z    P>|z|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
      tenure |   .1772948   .0152425    11.63   0.000       .14742    .2071696
         age |   .0191674   .0102686     1.87   0.062    -.0009588    .0392935
             |
 c.age#c.age |  -.0008496   .0001707    -4.98   0.000    -.0011842   -.0005149
             |
    not_smsa |  -.2119932   .0179604   -11.80   0.000    -.2471951   -.1767914
       _cons |    1.42761   .1509676     9.46   0.000     1.131719    1.723501
-------------+----------------------------------------------------------------
     sigma_u |  .33156584
     sigma_e |  .63029359
         rho |  .21674808   (fraction of variance due to u_i)
------------------------------------------------------------------------------
Instrumented:   tenure
Instruments:    age c.age#c.age not_smsa union south
------------------------------------------------------------------------------