Statistical inference for ectoparasiticide efficacy in animal trials

[摘要] In controlled animal trials of ectoparasiticides the e cacy of treatments is esti-mated based on the number of surviving parasites with which experimental animalshave been infected. Guidelines for the conduct and analysis of animal trials pub-lished by regulatory authorities require that the e cacy of the test treatment (asdetermined by the Abbott formula) should be at least 90%, for the test treatmentto be declared e cacious. This decision rule, therefore, is simply based on a pointestimate of e cacy and does not take into account the precision of the estimate;speci cally, proper statistical inference on the e cacy of the test treatment inquestion is not required. As a consequence, the Type I error probability of falselydeclaring a non-e cacious product to be e cacious can be overinated. In theproposed research project we investigate the use of appropriate statistical decisionrules for the e cacy which control the Type I error at a speci ed low level, say 5%.The statistical model for the data assumes a beta-binomial distribution which canaccommodate the binomial overdispersion typically associated with such data. ABayesian approach for implementing the analysis of ectoparasiticide e cacy datais explored.

[发布机构] University of the Free State