Mata Steps

[Nida Jamil]

Hi All,

I want to estimate productivity and the Beta's

I am running the GMM in MATA:

My program file is as follows:

Step 1:
Simple OLS to get the initial Beta values.

reg logdeflatedrevenue logcapital logmaterials loglabor

gen bols_l=_b[ loglabor ]
gen bols_k=_b[ logcapital ]
gen bols_m=_b[ logmaterials ]

reg logdeflatedrevenue logcapital logmaterials loglabor laglogcap lagloglab laglogmat

predict phi
gen phi_lag=L.phi

Step 2:
. mata
------------------------------------------------- mata (type end to exit) -----------------------------------------------
: void GMM_DL(todo,betas,crit,g,H)
> {
> PHI=st_data(.,("phi"))
> PHI_LAG=st_data(.,("phi_lag"))
> Z=st_data(.,(" laglogcap lagloglab laglogmat "))
> X=st_data(.,(" logcapital logmaterials loglabor "))
> X_lag=st_data(.,(" laglogcap lagloglab laglogmat" ))
> Y=st_data(.,(" logdeflatedrevenue "))
> QR_lag=st_data(.,(" logprevioustariff "))
> C=st_data(.,("const"))
> OMEGA=PHI-X*betas'
> OMEGA_lag=PHI_LAG-X_lag*betas'
> OMEGA_lag_pol=(C,OMEGA_lag,QR_lag)
> g_b = invsym(OMEGA_lag_pol'OMEGA_lag_pol)*OMEGA_lag_pol' OMEGA
> XI=OMEGA-OMEGA_lag_pol*g_b
> crit=(Z'XI)'(Z'XI)
> }



: void DL()
> {
> S=optimize_init()
> optimize_init_evaluator(S, &GMM_DL())
> optimize_init_evaluatortype(S,"d0")
> optimize_init_technique(S, "nm")
> optimize_init_nmsimplexdeltas(S, "select value")
> optimize_init_which(S,"min")
> optimize_init_params(S,(" bols_l bols_k bols_m "'))
> p=optimize(S)
> p
> st_matrix("beta_DL",p)
> }

: end
-------------------------------------------------------------------------------------------------------------------------

cap program drop dl
program dl, rclass
preserve
sort N time
mata DL()
end


Question: what is my next step? how can I get OMEGA and my beta's?? Can anyone share a link or some steps. Will this estimate productivity using LP or OP? What are the next commands?

Thanks!