Revisiting the Question - Does Corporate Headquarters Location Matter for Stock Returns?

We show that the ordinary least-squares method used by Pirinsky and Wang (2006) suffers from an endogeneity problem leading to biased and inconsistent estimates. A maximum likelihood estimation procedure that will produce consistent estimates for their model is set forth. This is done using an equivalent reformulation of their model and techniques for modeling data that exhibit observation-level dependence. In addition, we show how to correctly interpret the consistent maximum likelihood parameter estimates from the reformulated model in the context of their application