|From||"Pedace, Roberto" <Roberto_Pedace@redlands.edu>|
|Subject||st: Two-stage Tobit estimation|
|Date||Thu, 18 Sep 2003 15:17:49 -0700|
I have a couple of questions regarding Tobit estimation in STATA.
(1) Does the 'ivtobit' command produce the corrected standard errors estimates as discussed in Murphy and Topel (1985 - Journal of Business and Economic Statistics)? The need to account for the variability in the explanatory variable that is introduced through the two-step procedure is apparent. However, it seems that additional care must be taken when adjusting the covariance matrix in nonlinear estimations (e.g., Tobit).
(2) Are there any programs available to run a two-stage Tobit with panel data?
Department of Economics
University of Redlands
Redlands, CA 92373
tel: 909-793-2121, x2611