Richard J. Smith, University of Cambridge
Jaap Abbring, Tilburg University
Michael Jansson, Berkeley
Oliver Linton, University of Cambridge
Andrew Patton, Duke University
The Editorial Board of The Econometrics Journal, at the invitation of the Royal Economic Society, recently undertook a review of its editorial... Read more
Special Issue 2013
The first paper in this Special Issue authored by Charles Manski (Northwestern University) deals with the question of causal inference in a model with social interaction. The paper sets up a framework to deal with inference in models in which treatments and/or outcomes of others can affect directly one’s own outcome. The paper analyzes the identification question of standard treatment effects under various assumptions giving various interesting views on the roles of the reduced and structural forms.
The paper by Jan Kiviet (Nanyang Technological University and University of Amsterdam) examines the behaviour of both instrumental variable (IV) and ordinary least squares estimators under various assumptions on information sets and sampling schemes. The paper analyzes the question of what can be learned about the regression parameter when the standard zero correlation assumption between IV and error is replaced by an interval restriction on the correlation between endogenous regressor and error.
Tatiana Komarova (London School of Economics) examines the identification problem in second price auctions with arbitrary correlation in the valuations. She maps the problem into one of a generalized competing risks model and derives bounds on the joint valuation distribution. Also, the bounds are shown to improve when assumptions on the dependence among player valuations are used.
In their paper, Ismael Mourifié and Marc Henry (Université de Montréal) provide interesting inference methods for incomplete models with latent variables based on the recent work by Ekeland et al. (Ekeland, I., A. Galichon and M. Henry (2010): “Optimal transportation and the falsifiability of incompletely specified economic models,”Economic Theory, 42, 355–374). They provide methods for building confidence regions for the partially identified parameter vector based on valid bootstrap procedures.
This Special Issue of The Econometrics Journal collects a subset of papers from the 21st meeting of (EC)2 (European Conferences of the Econom(etr)ics Community in Econometrics and Quantitative Economics) held on the campus of the Toulouse School of Economics on December 17–18, 2010
For more information please visit : http://www.res.org.uk/view/pubSpeIssuePapers.html
The Econometrics Journal has a new Replication Policy for accepted papers
To benefit readers of accepted papers a new facility for supporting material linked to the online published manuscript is available.