|
A Test for Misspecification in the Censored Normal Model
Forrest D. Nelson
Abstract
Estimates of parameters in Tobit and other models for limited, truncated and censored dependent variables are not robust against misspecification. A test of the standard assumptions against a general misspecified alternative in the univariate censored normal model is derived and extended to the Tobit regression case. Computational ease and freedom from specification of a specific alternative hypothesis are primary attractions of the test.
|
