Panel Models with Two Threshold Variables: The Case of Financial Constraints

Threshold estimation methods are developed for panels with two threshold variables with individual fixed specific effects covering short time periods. Least squares estimation of the threshold and regression slopes is proposed... [ view full abstract ]

Threshold estimation methods are developed for panels with two threshold variables with individual fixed specific effects covering short time periods. Least squares estimation of the threshold and regression slopes is proposed using fixed-effects transformations in the static panel data model; while in the dynamic panel data model, maximum Likelihood estimation of the threshold and slope parameters is proposed using first difference transformations. The methods are applied to a 15-year sample of 565 US firms to test whether financial constraints affect investment decisions.