Dear all,

Lately we got a new command to deal with the endogeneity issues, "xthenreg", but still some ambiguity about how to interpret results etc. so we have to wait.

But i find an article* deals with this issue differently

"" To estimate this dynamic panel model, we follow a three-stage procedure: First, the endogenous variable is regressed on a set of instruments. For instruments, we use higher lags of the dependent variable.Second, the instrumental regression is estimated and the threshold value is determined by the method of Hansen (1999). Finally, the slope coefficients of the equation are estimated by using GMM procedures.""

i hope if someone can explain more this three-stage procedure


* Nonlinear Relationship between Institutional Factors and FDI Flows: Dynamic Panel Threshold Analysis. (Kurul (2017))


kind regards,
SEDKI