求助！GMM回归结果后没有报告r方是为什么呢？具体回归结果如下。

具体回归结果如下。该模型为静态面板，短面板，固定效应。模型存在异方差。FWYGDP代表服务业GDP，FWMYJK代表服务贸易进口。其他次回归都没有出现这种情况，求助大家看看存在什么问题。
ivregress gmm lnFWYGDP (lnFWMYJK lnFWMYCK=L.lnFWMYJK L.FWMYCK) lnGDPDEFL lnGDPGR

Instrumental variables (GMM) regression           Number of obs   =        629
                                                                        Wald chi2(4)    =      49.53
                                                                        Prob > chi2     =     0.0000
                                                                        R-squared       =          .
GMM weight matrix: Robust                         Root MSE        =     3.8695

------------------------------------------------------------------------------
             |               Robust
    lnFWYGDP |      Coef.   Std. Err.      z    P>|z|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
    lnFWMYJK |  -3.130086    1.16564    -2.69   0.007    -5.414698   -.8454743
    lnFWMYCK |   3.332657   1.088345     3.06   0.002      1.19954    5.465773
   lnGDPDEFL |   .3854096   .2014811     1.91   0.056     -.009486    .7803052
     lnGDPGR |  -.4835312   .2301416    -2.10   0.036    -.9346004    -.032462
       _cons |   2.648877   2.179437     1.22   0.224    -1.622741    6.920495
------------------------------------------------------------------------------
Instrumented:  lnFWMYJK lnFWMYCK
Instruments:   lnGDPDEFL lnGDPGR L.lnFWMYJK L.FWMYCK

基本上，用 IV 估计的 R^2 并不具意义（所以教科书所不用报告或不计算），虽然有的 Stata 指令会尝试报告 R^2 (但其与你所想像的 R^2 是不一样的)。

黃河泉 发表于 2018-5-12 09:58
基本上，用 IV 估计的 R^2 并不具意义（所以教科书所不用报告或不计算），虽然有的 Stata 指令会尝试报告 R ...

啊谢谢您

The short answer
MissingR2s, negativeR2s, and negative model sum of squares are all the same issue.

Stata’sivregresscommand suppresses the printing of anR2on 2SLS/IV if theR2is negative, which is to say, if the model sum of squares is negative.

Whether a negativeR2should be reported or simply suppressed is a matter of taste. At any rate, theR2really has no statistical meaning in the context of 2SLS/IV.

If it makes you feel better, you can compute theR2yourself from the returned results (seeAn examplesection of the FAQ).

For two-stage least squares, some of the regressors enter the model as instruments when the parameters are estimated. However, since our goal is to estimate the structural model, the actual values, not the instruments for the endogenous right-hand-side variables, are used to determine the model sum of squares (MSS). The model’s residuals are computed over a set of regressors different from those used to fit the model. This means a constant-only model of the dependent variable isnotnested within the two-stage least-squares model, even though the two-stage model estimates an intercept, and the residual sum of squares (RSS) is no longer constrained to be smaller than the total sum of squares (TSS). When RSS exceeds TSS, the MSS and theR2will be negative.

摘自：https://www.douban.com/group/topic/146072497/

The short answer
MissingR2s, negativeR2s, and negative model sum of squares are all the same issue.

Stata’sivregresscommand suppresses the printing of anR2on 2SLS/IV if theR2is negative, which is to say, if the model sum of squares is negative.

Whether a negativeR2should be reported or simply suppressed is a matter of taste. At any rate, theR2really has no statistical meaning in the context of 2SLS/IV.

If it makes you feel better, you can compute theR2yourself from the returned results (seeAn examplesection of the FAQ).

For two-stage least squares, some of the regressors enter the model as instruments when the parameters are estimated. However, since our goal is to estimate the structural model, the actual values, not the instruments for the endogenous right-hand-side variables, are used to determine the model sum of squares (MSS). The model’s residuals are computed over a set of regressors different from those used to fit the model. This means a constant-only model of the dependent variable isnotnested within the two-stage least-squares model, even though the two-stage model estimates an intercept, and the residual sum of squares (RSS) is no longer constrained to be smaller than the total sum of squares (TSS). When RSS exceeds TSS, the MSS and theR2will be negative.

摘自：https://www.douban.com/group/topic/146072497/