Hiroshima Mathematical Journal

Model selection criterion based on the prediction mean squared error in generalized estimating equations

Yu Inatsu and Shinpei Imori

Full-text: Open access

Abstract

The present paper considers a model selection criterion in regression models using generalized estimating equation (GEE). Using the prediction mean squared error (PMSE) normalized by the covariance matrix, we propose a new model selection criterion called PMSEG that reflects the correlation between responses. Numerical studies reveal that the PMSEG has better performance than previous other criteria for model selection.

Article information

Source
Hiroshima Math. J., Volume 48, Number 3 (2018), 307-334.

Dates
Received: 7 January 2017
Revised: 5 June 2018
First available in Project Euclid: 8 December 2018

Permanent link to this document
https://projecteuclid.org/euclid.hmj/1544238030

Digital Object Identifier
doi:10.32917/hmj/1544238030

Mathematical Reviews number (MathSciNet)
MR3885264

Zentralblatt MATH identifier
07032360

Subjects
Primary: 62H12: Estimation
Secondary: 62F07: Ranking and selection

Keywords
generalized estimating equations longitudinal data prediction mean squared error model selection

Citation

Inatsu, Yu; Imori, Shinpei. Model selection criterion based on the prediction mean squared error in generalized estimating equations. Hiroshima Math. J. 48 (2018), no. 3, 307--334. doi:10.32917/hmj/1544238030. https://projecteuclid.org/euclid.hmj/1544238030


Export citation