Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/241962 
Year of Publication: 
2021
Series/Report no.: 
cemmap working paper No. CWP26/21
Publisher: 
Centre for Microdata Methods and Practice (cemmap), London
Abstract: 
This paper studies models of processes generating censored outcomes with endogenous explanatory variables and instrumental variable restrictions. Tobit-type left censoring at zero is the primary focus in the exposition. The models studied here are unrestrictive relative to others widely used in practice, so they are relatively robust to misspeciÖcation. The models do not specify the process determining endogenous explanatory variables and they do not embody restrictions justifying control function approaches. The models can be partially or point identifying. IdentiÖed sets are characterized and it is shown how inference can be performed on scalar functions of partially identiÖed parameters when exogenous variables have rich support. In an application using data on UK household tobacco expenditures inference is conducted on the coeffi cient of an endogenous total expenditure variable with and without a Gaussian distributional restriction on the unobservable and compared with the results obtained using a point identifying complete triangular model.
Subjects: 
censored models
endogeneity
incomplete models
instrumental variables
partial identiÖcation
random sets
JEL: 
C10
C24
C26
C51
Persistent Identifier of the first edition: 
Document Type: 
Working Paper

Files in This Item:
File
Size
427.72 kB





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.