I'm estimating a model with a lagged dependent variable and fixed effects for panel units. I understand that this can result in Nickell Bias but I didn't think it would be a big problem because there are more time periods than panel units. A reviewer has asked that we demonstrate that Nickell Bias is not a problem. How might I go about this? I understand the Sargan-Hansen test is potentially useful, but I've only seen it applied to generalized method of moments (GMM) estimators. Is it possible to run something like Sargan-Hansen in the context of a regular LDV model?
Thanks!
