Assessing the error probability of the model selection test

Annals of the Institute of Statistical Mathematics

Volumn 49, Issue 3, 1997, Pages 395-410

  Shimodaira, Hidetoshi ^a,b  

^a UNIVERSITY OF TOKYO   (Japan)

^b INSTITUTE OF STATISTICAL MATHEMATICS   (Japan)

Author keywords

Akaike's information criterion; Canonical correlation coefficient; Error probability; Fixed alternatives; Local alternatives; Model selection; Test on expected discrepancies

Indexed keywords

EID: 9844221955     PISSN: 00203157     EISSN: None     Source Type: Journal    
DOI: 10.1023/A:1003140609666     Document Type: Article

References (6)

1. Cox, D. R. (1962). Further results on tests of separate families of hypotheses, J. Roy. Statist. Soc. Ser. B, 24, 406-424.
2. Hotelling, H. (1936). Relations between two sets of variables, Biometrika, 28, 321-377.
3. Linhart, H. (1988). A test whether two AIC's differ significantly, South African Statist. J., 22, 153-161.
4. Shimodaira, H. (1995). A Study on Statistical Model Selection - Construction of the Confidence Set of Models, Ph.D. dissertation, Department of mathematical engineering and information physics, University of Tokyo (in Japanese).
5. Shimodaira, H. (1996). An application of multiple comparison techniques to model selection, Ann. Inst. Statist. Math. (to appear).
6. Steiger, J. H., Shapiro, A. and Browne, M. W. (1985). On the multivariate asymptotic distribution of sequential chi-square statistics, Psychometrika, 50, 253-264.