This "readme" file gives some basic information about the following five Stata commands:
gmmhar (in ado file gmmhar.ado)
TS_GMM_F_all (in ado file TS_GMM_F_all.ado)
TS_GMM_t (in ado file TS_GMM_t.ado)
gmmhar_tab (in ado file gmmhar_tab.ado)
gmmhart (in ado file gmmhart.ado)

gmmhar.ado is the main procedure, and the other are the sub-procedures (TS_GMM_F_all.ado;TS_GMM_t.ado;gmmhar_tab.ado) that are used by the gmmhar commamd.

The program "gmmhar_tab.ado" tabulates the estimation results including coef, std err, t statistics, df, p-value, and confidence region.


The program "TS_GMM_F_all.ado" calculates the data-driven optimal K and the F statistic for testing the overall significance (the significance of all coefficients except the intercept)
See Sun (2017). The program also compuates the J statistic for overidentification in Sun and Kim (2012).

The program "TS_GMM_t.ado" computes the two-step gmm coefficient vector, the data-driven optimal K, the adjusted std error, the degrees of freedom, and the
t statistic for testing a single restriction. See Sun (2017).



gmmhart.ado performs Wald tests of simple and composite linear hypotheses about the parameters in the most recently estimated gmmhar model.


gout1.do-gout2.do are used to produce case6-case7 in the paper. ghtest1.do produces case 11 in the paper.


Place all of the .ado files in a directory where Stata can find them.