Annals of the Institute of Statistical Mathematics

, Volume 55, Issue 3, pp 537–553 | Cite as

Corrected versions of cross-validation criteria for selecting multivariate regression and growth curve models

  • Yasunori Fujikoshi
  • Takafumi Noguchi
  • Megu Ohtaki
  • Hirokazu Yanagihara
Cross-validation

Abstract

This paper is concerned with cross-validation (CV) criteria for choice of models, which can be regarded as approximately unbiased estimators for two types of risk functions. One is AIC type of risk or equivalently the expected Kullback-Leibler distance between the distributions of observations under a candidate model and the true model. The other is based on the expected mean squared error of prediction. In this paper we study asymptotic properties of CV criteria for selecting multivariate regression models and growth curve models under the assumption that a candidate model includes the true model. Based on the results, we propose their corrected versions which are more nearly unbiased for their risks. Through numerical experiments, some tendency of the CV criteria will be also pointed.

Key words and phrases

CV criterion corrected versions growth curve models model selection multivariate regression models risk 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Akaike, H. (1973). Information theory and an extension of the maximum likelihood principle,2nd International Symposium on Information Theory (eds. B. N. Petrov and F. Csáki), 267–281, Akadémia Kiado, Budapest.Google Scholar
  2. Anderson, T. W. (1984).An Introduction to Multivariate Analysis, 2nd ed., John Wiley & Sons, New York.Google Scholar
  3. Bedrick, E. J. and Tsai, C. L. (1994). Model selection for multivariate regression in small samples,Biometrics,76, 226–231.CrossRefGoogle Scholar
  4. Fujikoshi, Y. and Satoh, K. (1994). Modified AIC andC p in multivariate linear regression,Biometrika,84, 707–716.MathSciNetCrossRefGoogle Scholar
  5. Gleser, L. J. and Olkin, I. (1970). Linear models in multivariate analysis,Essays in Probability and Statistics (eds. R. C. Bose, I. M. Chakravarti, P. C. Mahalanobis, C. R. Rao and K. J. C. Smith, University of North Carolina Press, Chapel Hill, North Carolina.Google Scholar
  6. Mallows, C. L. (1973). Some comments onC p,Technometrics,15, 661–675.MATHCrossRefGoogle Scholar
  7. Potthoff, R. F. and Roy, S. N. (1964). A generalized multivariate analysis of variance model useful especially for growth curve problems,Biometrika,51, 313–325.MATHMathSciNetCrossRefGoogle Scholar
  8. Satoh, K., Kobayashi, M. and Fujikoshi, Y. (1997). Variable selection for the growth curve model,J. Multivariate Anal.,60, 277–292.MATHMathSciNetCrossRefGoogle Scholar
  9. Siotani, M., Hayakawa, T. and Fujikoshi, Y. (1985).Modern Multivariate Statistical Analysis: A Graduate Course and Handbook, American Sciences Press, Columbus, Ohio.Google Scholar
  10. Stone, M. (1974). Cross-validation and multinomial prediction,Biometrika,61, 509–515.MATHMathSciNetCrossRefGoogle Scholar
  11. Stone, M. (1977). An asymptotic equivalence of choice of model by cross-validation and Akaike's criterion,J. Roy. Statist. Soc. Ser. B,39, 44–47.MATHMathSciNetGoogle Scholar
  12. Sugiura, N. (1978). Further analysis of the data by Akaike's information criterion and the finite corrections,Comm. Statist. Theory Methods,7, 13–26.MathSciNetGoogle Scholar

Copyright information

© The Institute of Statistical Mathematics 2003

Authors and Affiliations

  • Yasunori Fujikoshi
    • 1
  • Takafumi Noguchi
    • 1
  • Megu Ohtaki
    • 2
  • Hirokazu Yanagihara
    • 3
  1. 1.Department of Mathematics, Graduate School of ScienceHiroshima UniversityHigashi-HiroshimaJapan
  2. 2.Department of Environmentrics and Biometrics, Research Institute for Radiation Biology and MedicineHiroshima UniversityHiroshimaJapan
  3. 3.Department of Statistical MethodologyThe Institute of Statistical MathematicsTokyoJapan

Personalised recommendations