Titelaufnahme

Titel
Estimating fixed effects: perfect prediction and bias in binary response panel models, with an application to the hospital readmissions reduction program / Johannes S. Kunz (Monash University), Kevin E. Staub (University of Melbourne and IZA), Rainer Winkelmann (University of Zurich and IZA) ; IZA Institute of Labor Economics
VerfasserKunz, Johannes In der Gemeinsamen Normdatei der DNB nachschlagen ; Staub, Kevin E. In der Gemeinsamen Normdatei der DNB nachschlagen ; Winkelmann, Rainer In der Gemeinsamen Normdatei der DNB nachschlagen
KörperschaftForschungsinstitut zur Zukunft der Arbeit In der Gemeinsamen Normdatei der DNB nachschlagen
ErschienenBonn, Germany : IZA Institute of Labor Economics, November 2017
Ausgabe
Elektronische Ressource
Umfang1 Online-Ressource (44 Seiten) : Diagramme
SerieDiscussion paper ; no. 11182
URNurn:nbn:de:hbz:5:2-144197 Persistent Identifier (URN)
Zugriffsbeschränkung
 Das Dokument ist frei verfügbar.
Volltexte
Estimating fixed effects: perfect prediction and bias in binary response panel models, with an application to the hospital readmissions reduction program [4.13 mb]
Links
Nachweis
Verfügbarkeit In meiner Bibliothek
Zusammenfassung

The maximum likelihood estimator for the regression coefficients, , in a panel binary response model with fixed effects can be severely biased if N is large and T is small, a consequence of the incidental parameters problem. This has led to the development of conditional maximum likelihood estimators and, more recently, to estimators that remove the O(T-1) bias in ^. We add to this literature in two important ways. First, we focus on estimation of the fixed effects proper, as these have become increasingly important in applied work. Second, we build on a bias-reduction approach originally developed by Kosmidis and Firth (2009) for cross-section data, and show that in contrast to other proposals, the new estimator ensures finiteness of the fixed effects even in the absence of within-unit variation in the outcome. Results from a simulation study document favourable small sample properties. In an application to hospital data on patient readmission rates under the 2010 Affordable Care Act, we find that hospital fixed effects are strongly correlated across different treatment categories and on average higher for privately owned hospitals.