On Uniformly Balanced Crossover Designs Efficient Under Subject Dropout
Design selection is examined for crossover studies under the situation that subjects may terminate prior to fulfilling the treatment sequences. Construction and efficiency of a class of designs, called Uniformly Balanced Designs Balanced for Loss, is examined.
AMS Subject Classification62K05 05B15
KeywordsCrossover study Latin square Precision loss Repeated measurement design Subject dropout Universal optimality
Unable to display preview. Download preview PDF.
- Dudeney, H. E. 1958. Amusements in mathematics. New York, Dover Publications.Google Scholar
- Jones, B., and M. G. Kenwood. 2003. Design and analysis of cross-over trials. London, CRC Press.Google Scholar
- Kiefer, J. 1975. Construction and optimality of generalized Youden designs. In A survey of statistical design and linear models, ed. J. N. Srivastava, 333–353. Amsterdam, North Holland.Google Scholar
- Ratkowsky, D. A., M. A. Evans, and J. R. Alldredge. 1992. Cross-over experiments: Design, analysis and application. New York, Marcel Dekker.Google Scholar