Hello everyone,
I'm estimating a dynamic panel model with two-step difference gmm:
The regression could be summarize in this way:
theoretically Y(t-1) is an endogenous variable[might be correlated with contemporaneous and past errors] and X1(t-1), X2(t-1) and X3(t-1) are predetermined [variable is uncorrelated with the contemporaneous and all future idiosyncratic errors but might be correlated with past errors].
however, I am having difficulty where knowing to place the predetermined variables in the xtabond2 syntax, in gmm() or ivstyle(). I suppose it must be inside gmm(). So I'm coding this:
So my only question is where shoul I write the predetermined variables inside gmm() or iv()?
I'm estimating a dynamic panel model with two-step difference gmm:
The regression could be summarize in this way:
Code:
Y=Y(t-1)+X1(t-1)+X2(t-1)+X3(t-1) + i.year
however, I am having difficulty where knowing to place the predetermined variables in the xtabond2 syntax, in gmm() or ivstyle(). I suppose it must be inside gmm(). So I'm coding this:
Code:
xtabond2Y Y(t-1) X1(t-1) X2(t-1) X3(t-1) i.year, gmm (Y Y(t-1) X1(t-1) X2(t-1) X3(t-1), collapse) iv(i.year) nolevelq twostep robust small orthogonal
