Score contribution per author:
α: calibrated so average coauthorship-adjusted count equals average raw count
In this paper, we introduce a regime switching panel data model with interactive fixed effects. We propose a maximum likelihood estimation method and develop an expectation and conditional maximization algorithm to estimate the unknown parameters. Simulation results show that the algorithm works well in finite samples. The biases of the maximum likelihood estimates are negligible and the root mean squared errors of the maximum likelihood estimates decrease with the increase of either the number of the cross-sectional units N or the size of the time periods T.