CIRJE-F- 503. Kunitomo, Naoto and Kentaro Akashi, "The Conditional Limited Information Maximum Likelihood Approach to Dynamic Panel Structural Equations", July 2007.

We propose the conditional limited information maximum likelihood (CLIML) approach for estimating dynamic panel structural equation models. When there are dynamic effects and endogenous variables with individual effects at the same time, the CLIML estimation method for the doubly-filtered data does give not only a consistent estimation, but also it attains the asymptotic efficiency when the number of orthogonal condition is large. Our formulation includes Alvarez and Arellano (2003), Blundell and Bond (2000) and other linear dynamic panel models as special cases.