论文信息 - Optimal Designs for Discriminating among Several Non-Normal Models

Optimal Designs for Discriminating among Several Non-Normal Models

Typically T-optimality is used to discriminate among several models with Normal errors. In order to discriminate between two non-Normal models, a criterion based on the Kullback-Liebler distance has been proposed, the so called KL-criterion. In this paper, a generalization of the KL-criterion is proposed to deal with discrimination among several non-Normal models. An example where three logistic regression models are compared is provided.

Chiara Tommasi | C. Tommasi

[1] W. J. Studden,et al. Theory Of Optimal Experiments , 1972 .

[2] D. Cox,et al. Planning Experiments for Discriminating between Models , 1974 .

[3] David R. Anderson,et al. Model selection and inference : a practical information-theoretic approach , 2000 .

[4] A. Atkinson,et al. The design of experiments for discriminating between two rival models , 1975 .

[5] Anthony C. Atkinson,et al. Planning experiments to detect inadequate regression models , 1972 .

[6] Dariusz Ucinski,et al. T -Optimum Designs for Multiresponse Dynamic Heteroscedastic Models , 2004 .

[7] Anthony C. Atkinson,et al. The Design of Experiments to Discriminate Between Two Rival Generalized Linear Models , 1992 .

[8] Henry P. Wynn,et al. MODA 7 - advances in model-oriented design and analysis : proceedings of the 7th international workshop on Model-oriented design and analysis, held in Heeze, The Netherlands, June 14-18, 2004 , 2004 .

[9] J. López Fidalgo,et al. Optimal designs for discriminating between heteroscedastic models , 2005 .

[10] Steven E. Rigdon,et al. Model-Oriented Design of Experiments , 1997, Technometrics.

[11] J. López–Fidalgo,et al. An optimal experimental design criterion for discriminating between non‐normal models , 2007 .

[12] H. Wynn. The Sequential Generation of $D$-Optimum Experimental Designs , 1970 .

[13] A. Atkinson,et al. Optimal design : Experiments for discriminating between several models , 1975 .