Hostname: page-component-78c5997874-t5tsf Total loading time: 0 Render date: 2024-11-19T07:18:56.919Z Has data issue: false hasContentIssue false
  • English
  • Français

Selection of Credibility Regression Models

Published online by Cambridge University Press:  29 August 2014

Peter Bühlmann  and
Hans Bühlmann
Peter Bühlmann*
Affiliation:
ETH Zürich, Switzerland
Hans Bühlmann*
Affiliation:
ETH Zürich, Switzerland
*
Seminar für Statistik, ETH Zürich, CH-8092 Zürich, SwitzerlandE-mail:[email protected]
Departement Mathematik, ETH Zürich, CH-8092 Zürich, SwitzerlandE-mail:[email protected]
Rights & Permissions [Opens in a new window]

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the ‘Save PDF’ action button.

We derive some decision rules to select best predictive regression models in a credibility context, that is, in a “random effects’ linear regression model with replicates. In contrast to usual model selection techniques on a collective level, our proposal allows to detect individual structures, even if they disappear in the collective.

We give exact, non-asymptotic results for the expected squared error loss for a predictor based on credibility estimation in different models. This involves correct accounting of random model parameters and the study of expected loss for shrinkage estimation. We support the theoretical properties of the new model selectors by a small simulation experiment.

Keywords

Bias-variance trade-offEmpirical BayesRandom effects modelShrinkage estimationSquared prediction lossSubset-regression
Type
Articles
Information
ASTIN Bulletin: The Journal of the IAA , Volume 29 , Issue 2 , November 1999 , pp. 245 - 270
Copyright
Copyright © International Actuarial Association 1999

References

[1]Akaike, H. (1970). Statistical predictor identification. Annals of the Institute of Statistical Mathematics 22, 203–217.CrossRefGoogle Scholar
[2]Akaike, H. (1973). Information theory and the maximum likelihood principle. In 2nd International Symposium on Information Theory (Eds. Petrov, B.N. & Csàki, F.), Akademiai Kiàdo, Budapest.Google Scholar
[3]Bühlmann, H. and Gisler, A. (1997). Credibility in the regression case revisited (A late tribute to Charles A. Hachemeister). ASTIN Bulletin 27, 83–98.CrossRefGoogle Scholar
[4]Gelfand, A. and Gosh, S. (1998). A minimum posterior predictive loss approach. Biometrika 85, 1–11.CrossRefGoogle Scholar
[5]Hachemeister, C.A. (1975). Credibility for regression models with application to trend. In Credibility, theory and application, Proc. of the Berkeley Actuarial Research Conference on Credibility, pp. 129–163. Academic Press.Google Scholar
[6]Jewell, W.S. (1975). The use of collateral data in credibility theory: a hierarchical model. Giornale dellTnstituto Italiano degli Attuari 38, 1–16.Google Scholar
[7]Klotz, J.H., Milton, R.C. and Zacks, S. (1969). Mean square efficiency of estimators of variance components. Journal of the American Statistical Association, 64, 1383–1402.CrossRefGoogle Scholar
[8]Linhart, H. and Zucchini, W. (1986). Model Selection. Wiley.Google Scholar
[9]Mallows, C.L. (1973). Some comments on Cp. Technometrics 15, 661–675.Google Scholar
[10]Jneuhaus, W. (1985). Choice of statistics in linear Bayes estimation. Scandinavian Actuarial Journal, 1–26.CrossRefGoogle Scholar
[11]Norberg, R. (1986). Hierarchical credibility: analysis of a random effect linear model with nested classification. Scandinavian Actuarial Journal, 204–222.CrossRefGoogle Scholar
[12]Rissanen, J. (1989). Stochastic Complexity in Statistical Inquiry. World Scientific.Google Scholar
[13]Schwarz, G. (1978). Estimating the dimension of a model. Annals of Statistics 6, 461–464.CrossRefGoogle Scholar
[14]Sundt, B. (1979). A hierarchical regression credibility model. Scandinavian Actuarial Journal, 107–114.CrossRefGoogle Scholar
[15]Taylor, G.C. (1979). Credibility analysis of a general hierarchical model. Scandinavian Actuarial Journal, 1–12.CrossRefGoogle Scholar
[16]Weisberg, S. (1985). Applied Linear Regression. Wiley.Google Scholar