Header

UZH-Logo

Maintenance Infos

Predicting fixed effects in panel probit models


Kunz, Johannes S; Staub, Kevin E; Winkelmann, Rainer (2018). Predicting fixed effects in panel probit models. HEDG Working Paper series 18/23, University of York, Department of Economics and Related Studies.

Abstract

We present a method to estimate and predict fixed effects in a panel probit model when N is large and T is small, and when there is a high proportion of individual units without variation in the binary response. Our approach builds on a bias-reduction method originally developed by Kosmidis and Firth (2009) for cross-section data. In contrast to other estimators, our approach ensures that predicted fixed effects are finite in all cases. Results from a simulation study document favorable properties in terms of bias and mean squared error. The estimator is applied to predict period-specific fixed effects for the extensive margin of health care utilization (any visit to a doctor during the previous three months), using German data for 2000-2014. We find a negative correlation between fixed effects and observed characteristics. Although there is some within-individual variation in fixed effects over sub-periods, the between-variation is four times as large.

Abstract

We present a method to estimate and predict fixed effects in a panel probit model when N is large and T is small, and when there is a high proportion of individual units without variation in the binary response. Our approach builds on a bias-reduction method originally developed by Kosmidis and Firth (2009) for cross-section data. In contrast to other estimators, our approach ensures that predicted fixed effects are finite in all cases. Results from a simulation study document favorable properties in terms of bias and mean squared error. The estimator is applied to predict period-specific fixed effects for the extensive margin of health care utilization (any visit to a doctor during the previous three months), using German data for 2000-2014. We find a negative correlation between fixed effects and observed characteristics. Although there is some within-individual variation in fixed effects over sub-periods, the between-variation is four times as large.

Statistics

Downloads

2 downloads since deposited on 22 Feb 2019
2 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Working Paper
Communities & Collections:03 Faculty of Economics > Department of Economics
Dewey Decimal Classification:330 Economics
JEL Classification:I11, I18, C23, C25
Uncontrolled Keywords:Perfect prediction, bias reduction, modified score function
Language:English
Date:August 2018
Deposited On:22 Feb 2019 13:58
Last Modified:22 Feb 2019 14:01
Series Name:HEDG Working Paper series
Number of Pages:31
ISSN:1751-1976
OA Status:Green
Official URL:https://www.york.ac.uk/economics/hedg/wps/wp2018/

Download

Download PDF  'Predicting fixed effects in panel probit models'.
Preview
Content: Published Version
Filetype: PDF
Size: 937kB