Summary
Finite sample selection criteria are derived for the case of multinomial operating and approximating models. The criteria are based on the Kullback-Leibler, the Gauß and the Pearsonchisquared discrepancies and turn out to be crossvalidatory.
Similar content being viewed by others
References
Linhart, H., Zucchini, W. (1982). On model selection in analysis of variance. In: B. Fleischmann et al., ed. 's, Oper. Res. Proceedings 1981, 483–493.
Linhart, H., Zucchini, W. (1985). Selection of approximating models by chisquared discrepancies if the operating model is multinomial. Statistics & Dec., Suppl. Issue No. 2, 375–380.
Linhart, H., Zucchini, W. (1986). Model selection. J. Wiley, New York.
Sakamoto, Y, Akaike, H. (1978). Analysis of cross-classified data by AIC. Ann. Inst. Statist. Math., 30, 185–197.
Stone, M. (1974). Cross-validatory choice and assessment of statistical predictions. J. Roy. Statist. soc. B. 36, 111–133.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Linhart, H., Zucchini, W. Finite sample selection criteria for multinomial models. Statistische Hefte 27, 173–178 (1986). https://doi.org/10.1007/BF02932566
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF02932566