App Stats: Kasy on "Identification in General Triangular Systems"

We hope you can join us this Wednesday, October 3, 2012 for the Applied Statistics Workshop. Maximilian Kasy, Assistant Professor of Economics from the Department of Economics at Harvard University, will give a presentation entitled "Identification in General Triangular Systems". A light lunch will be served at 12 pm and the talk will begin at 12.15.

"Identification in General Triangular Systems"
Maximilian Kasy
Department of Economics, Harvard University
CGIS K354 (1737 Cambridge St.)
Wednesday, October 3rd, 2012 12.00 pm

Abstract:

This paper discusses identification in continuous triangular systems without restrictions on heterogeneity or functional form. In particular, we do not assume separability of structural functions, restrictions on the dimensionality of unobservables, or monotonicity in unobservables. We do maintain monotonicity of the first stage relationship in the instrument. We show that under this condition alone, and given rich enough support of the data, we can achieve point identification of potential outcome distributions, and in particular of the average structural function. If the support of the continuous instrument is not large enough potential outcome distributions are partially identified. If the instrument is discrete identification fails completely. The setup discussed in this paper covers important cases not covered by existing approaches such as conditional moment restrictions (c.f. Newey and Powell, 2003) and control variables (c.f. Imbens and Newey, 2009). It covers, in particular, random coefficient models, as well as models arising as the reduced form of a system of structural equations.

Posted by Konstantin Kashin at September 30, 2012 11:28 PM