0

When running ivregress with and without a constant, I noticed that in case of noconst option the Wald chi2 and R-squared are missing.
Why would this happen?

Below is the simplest possible example using a random sample:

. ivregress 2sls Y (X=Z)

Instrumental variables (2SLS) regression          Number of obs   =         20
                                                  Wald chi2(1)    =       6.91
                                                  Prob > chi2     =     0.0086
                                                  R-squared       =     0.4562
                                                  Root MSE        =     .59624

------------------------------------------------------------------------------
           Y |      Coef.   Std. Err.      z    P>|z|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
           X |  -.9750557   .3709433    -2.63   0.009    -1.702091   -.2480202
       _cons |   1.005144   .3959347     2.54   0.011     .2291262    1.781162
------------------------------------------------------------------------------
Instrumented:  X
Instruments:   Z

. ivregress 2sls Y (X=Z), noconst

Instrumental variables (2SLS) regression          Number of obs   =         20
                                                  Wald chi2(1)    =          .
                                                  Prob > chi2     =          .
                                                  R-squared       =          .
                                                  Root MSE        =     .77568

------------------------------------------------------------------------------
           Y |      Coef.   Std. Err.      z    P>|z|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
           X |  -.2053355   .1732044    -1.19   0.236    -.5448099    .1341389
------------------------------------------------------------------------------
Instrumented:  X
Instruments:   Z

.

UPD: Please note that this question is cross-referenced at Statalist: https://www.statalist.org/forums/forum/general-stata-discussion/general/1406558-wald-chi2-missing-in-ivregress-without-intercept

cheesecake
  • 1
  • 1
  • You might get better answers on a Stata list. Note that removing the constant alters the model, see this answer from this site https://stats.stackexchange.com/questions/7948/when-is-it-ok-to-remove-the-intercept-in-a-linear-regression-model/127517#127517 – mdewey Aug 15 '17 at 15:29
  • @mdewey Thank you, I need to run a model without a constant for certain important reasons. Having realized the Wald chi2 is missing, I thought it might have something to do with the constant term. An example above is designed for exposition purpose, to show that Wald chi2 is missing in the simplest model possible with an arbitrary generated sample. – cheesecake Aug 16 '17 at 09:18

0 Answers0