We propose an estimation procedure for a semiparametric panel data censored regression model in which the error terms may be subject to general forms of nonstationarity. Specifically, we allow for heteroskedasticity over time and a time varying factor load on the individual specific effect....

It is often believed that without instruments, endogenous sample selection models are identified only if a covariate with a large support is available (see, e.g., Chamberlain, <xref>1986</xref>, <italic>Journal of Econometrics</italic> 32, 189–218; Lewbel, <xref>2007</xref>, <italic>Journal of Econometrics</italic>141, 777–806) . We propose a new...