Dear Statalists,

To control for endogeneity, can I use the Lag for the Discrete hazard proportional odd. For instance,

At first, setting the data as a panel:

xtset ID TIME

Then writing the following code:

logit Dep l.X1 l.X2 l.X3 l.X4 l.X5 e2 e3, nolog cluster (COMPID).


Thanks in advance.