could any one help in System GMM coding

[Emad Noureldeen]

Dear Stata users,

I try to use the System GMM approach for estimation. I want to test the impact of corporate governance on disclosure items.

The dependent variable (disclosure items): ITEMs
Independent variables (corporate governance): CEODUAL BDSIZE INDBD SUPSIZE INDSUP.
Control variables including SIZE AREC_INVT LOSS AUDFEE GENDER ROA BIG4 AUDOPIN CURR LEV TENURE SWITCH ChangeCPA.
The year and industry dummies: i.Year i.IND

According to the prior studies, I assume that the corporate governance variables are endogenous. So, CEODUAL BDSIZE INDBD SUPSIZE INDSUP are endogenous variables.

I use the following code

xtabond2 ITEMs L.ITEMs CEODUAL BDSIZE INDBD SUPSIZE INDSUP SIZE AREC_INVT LOSS AUDFEE GENDER ROA BIG4 AUDOPIN CURR LEV TENURE SWITCH ChangeCPA i.Year i.IND, gmm(L.ITEMs CEODUAL BDSIZE INDBD SUPSIZE INDSUP) iv(L.CEODUAL L.BDSIZE L.INDBD L.SUPSIZE L.INDSUP SIZE AREC_INVT LOSS AUDFEE GENDER ROA BIG4 AUDOPIN CURR LEV TENURE SWITCH ChangeCPA i.Year i.IND) small twostep robust orthogonal

But the results are not significant.

Then I use the following code

xtabond2 ITEMs L.ITEMs CEODUAL BDSIZE INDBD SUPSIZE INDSUP SIZE AREC_INVT LOSS AUDFEE GENDER ROA BIG4 AUDOPIN CURR LEV TENURE SWITCH ChangeCPA i.Year i.IND, gmm(ITEMs CEODUAL BDSIZE INDBD SUPSIZE INDSUP lag (2 4))  small twostep robust orthogonal

But it gives me gmmstyle(KAMs CEODUAL BDSIZE, INDBD SUPSIZE INDSUP lag(2 2)) invalid.

Could any one help me to write the right code? If it is possible to use the lag of corporate governance variables as instruments.