大概是因为中山大学连玉君老师与南开大学王群勇老师的 Stata 程序,我发现论坛中还有许多人在应用这个面板资料门槛模型 (Hansen, 1999)。记得我刚从美国毕业后回台湾时(1997),不久后就接触了这个模型,之后也有利用这个模型发表于SSCI之文章。如今也将近20年了,虽然不敢说该模型已经过时,但至少于模型本身贡献或其新颖度显然已经有稍不足之地方(所以,必须在文章主题等其他方面补足贡献,才有机会发表还可以之期刊)。所以,利用这机会,与大家分享一篇即将刊登的文章:Chudik, A., Mohaddes, K., Pesaran, M. H., and Raissi, M. (2016), "Is There a Debt-threshold Effect on Output Growth?" Forthcoming in Review of Economics and Statistics. 其中,有新的面板资料门槛模型,大家可以参考看看!
两者差异之处:Hansen (1999) considers the problem of estimation and testing of threshold effects in the case of static panels with fixed effects and homogeneous slopes, and deals with panels where the time dimension ($T$) is short and the cross section dimension ($N$) is large. He eliminates individual specific effects by de-meaning and as a result his approach cannot be extended to dynamic panels or panels with heterogeneous slopes. CMPR's (2016) model allows for (i) endogeneity of debt and growth, (ii) fixed effects, (iii) dynamics (homogeneous and heterogeneous), as well as (iv) cross-sectional error dependence.