Commentary and Review Series 1-93
Two methods for the analysis of chromosome aberration data from the atomic-bomb survivors: Quasi-likelihood moment method and beta-binomial method
Nakashima E, Ohtaki KJ Jpn Stat Soc 24(2):209-19, 1994
Summary
Two estimation methods, the maximum likelihood method under the beta-binomial model and the quasi-likelihood moment method based on the mean and variance relation, were applied to G-banding chromosome aberration data from Hiroshima atomic-bomb survivors. The chromosome aberration rate was empirically thought to be overdispersed by the intraindividual correlation or the radiation dose estimation error. Using the results of Pierce, Stram, Vaeth, and Schafer, the mean and variance relationship was formulated under the two variations to apply the quasi-likelihood method and the beta-binomial model. The quasi-likelihood moment method allows only single extra-binomial parameter but is robust, whereas the beta-binomial model allows for both dose error and intraindividual variations. Dose response parameter estimates obtained using the two methods were similar. However, the quasi-likelihood moment method is computationally less intensive than the beta-binomial maximum likelihood method. When observations are perturbed by the dose-error, the quasi-likelihood method is recommended.
Two estimation methods, the maximum likelihood method under the beta-binomial model and the quasi-likelihood moment method based on the mean and variance relation, were applied to G-banding chromosome aberration data from Hiroshima atomic-bomb survivors. The chromosome aberration rate was empirically thought to be overdispersed by the intraindividual correlation or the radiation dose estimation error. Using the results of Pierce, Stram, Vaeth, and Schafer, the mean and variance relationship was formulated under the two variations to apply the quasi-likelihood method and the beta-binomial model. The quasi-likelihood moment method allows only single extra-binomial parameter but is robust, whereas the beta-binomial model allows for both dose error and intraindividual variations. Dose response parameter estimates obtained using the two methods were similar. However, the quasi-likelihood moment method is computationally less intensive than the beta-binomial maximum likelihood method. When observations are perturbed by the dose-error, the quasi-likelihood method is recommended.