Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/108584 
Year of Publication: 
2012
Series/Report no.: 
Working Paper No. 1203
Publisher: 
Koç University-TÜSİAD Economic Research Forum (ERF), Istanbul
Abstract: 
We solve a class of identification problems for nonparametric and semiparametric models when the endogenous covariate is discrete with unbounded support. Then we proceed with an approach that resolves a polynomial basis problem for the above class of discrete distributions, and for the distributions given in the sufficient condition for completeness in Newey and Powell (2003). Thus, in addition to extending the set of econometric models for which nonparametric or semiparametric identification of structural functions is guaranteed to hold, our approach provides a natural way of estimating these functions. Finally, we extend our polynomial basis approach to Pearson-like and Ord-like families of distributions.
Subjects: 
nonparametric methods
identification
instrumental variables
Document Type: 
Working Paper

Files in This Item:
File
Size





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