Optimal design for the proportional odds model

The authors construct locally optimal designs for the proportional odds model for ordinal data. While they investigate the standard D-optimal design, they also investigate optimality criteria for the simultaneous estimation of multiple quantiles, namely DA -optimality and the omnibus criterion. The design of experiments for the simultaneous estimation of multiple quantiles is important in both toxic and effective dose studies in medicine. As with c-optimality in the binary response problem, the authors find that there are distinct phase changes when exploring extreme quantiles that require additional design points. The authors also investigate relative efficiencies of the criteria. Les auteurs elaborent des plans d'experience localement optimaux pour des donnees ordinales repondant a un modele a rapports de cotes proportionnels. En plus du plan D-optimal standard, ils explorent deux criteres d'optimalite, la DA-optimalite et un critere dit omnibus, permettant de repondre a un souci d'estimation simultanee de plusieurs quantiles. Cette preoccupation a son importance dans les etudes medicales de dosage et de toxicite. Les auteurs montrent qu'a l'instar de la c-optimalite dans les cas de reponses dichotomiques, le besoin d'estimer de quantiles extrěmes induit des changements de phase tres nets dans la taille des plans, fis etudient en outre l'efficacite relative de leurs criteres.

[1]  Lorens A. Imhof,et al.  Maximin designs for exponential growth models and heteroscedastic polynomial models , 2001 .

[2]  F. Pukelsheim Optimal Design of Experiments , 1993 .

[3]  C. Redmond,et al.  Base-line quality-of-life assessment in the National Surgical Adjuvant Breast and Bowel Project Breast Cancer Prevention Trial. , 1995, Journal of the National Cancer Institute.

[4]  W K Wong,et al.  A Graphical Method for Finding Maximin Efficiency Designs , 2000, Biometrics.

[5]  P. McCullagh Regression Models for Ordinal Data , 1980 .

[6]  W. J. Studden Elfving's Theorem and Optimal Designs for Quadratic Loss , 1971 .

[7]  G. Elfving Optimum Allocation in Linear Regression Theory , 1952 .

[8]  William F. Rosenberger,et al.  Restricted optimality for phase I clinical trials , 1998 .

[9]  Weng Kee Wong,et al.  New developments and applications in experimental design : selected proceedings of a 1997 Joint AMS-IMS-SIAM summer conference , 1998 .

[10]  K. Chaloner,et al.  Optimum experimental designs for properties of a compartmental model. , 1993, Biometrics.

[11]  A. Atkinson,et al.  Optimum Experimental Designs for Multinomial Logistic Models , 1999, Biometrics.

[12]  I. Ford,et al.  The Use of a Canonical Form in the Construction of Locally Optimal Designs for Non‐Linear Problems , 1992 .

[13]  Kathryn Chaloner,et al.  Optimal Designs for a Continuation-ratio Model , 2001 .

[14]  P. Laycock,et al.  Optimum Experimental Designs , 1995 .

[15]  J. Kiefer,et al.  The Equivalence of Two Extremum Problems , 1960, Canadian Journal of Mathematics.

[16]  William F Rosenberger,et al.  Competing designs for phase I clinical trials: a review , 2002, Statistics in medicine.