How informative is the initial condition in the dynamic panel model with fixed effects?

摘要

I consider estimation of the autoregressive panel model with fixed effects Y_(it) = c_i + #beta#Y_(i,t-1) + #epsilon#_(it). I investigate the estimation method developed by Blundell and Bond (1998), which makes use of the stationarity of the initial levels. I do it by numerically comparing the semiparametric information bounds for the case that incor-porates the stationarity of the initial condition and for the case that does not. It is found that the efficiency gain can be substantial.