Dynamic panels with threshold effect and endogeneity

This paper addresses an important issue of modeling nonlinear asymmetric dynamics and unobserved individual heterogeneity in the threshold panel data framework, simultaneously. As a general approach, we develop the first-differenced GMM estimator, which allows both threshold variable and regressors to be endogenous. When the threshold variable becomes strictly exogenous, we propose a more efficient two-step least squares estimator. We provide asymptotic theory and develop the testing procedure for threshold effects and the threshold variable exogeneity. Monte Carlo studies provide a support for theoretical predictions. We present an empirical application investigating an asymmetric sensitivity of investment to cash flows.