計量生物学 Vol. 37(2016) No. 2

Multiple comparison procedures provide differences among the groups that is of interest. The procedures are used in clinical trials and agricultural fields experiments. We consider multi-sample model with Bernoulli responses under simple ordered restrictions of proportions. Shiraishi (2014b) proposed closed testing procedures based on maximum values of two-sample test statistics for all pairwise comparisons. The equality of sample sizes is needed in the asymptotic theory of Shiraishi’s procedures. We propose closed testing procedures based on statistics having asymptotically a x̅ ²-distribution which is appeared in Chernoff (1954). The proposed procedures are applicable for the models with unequal sample sizes. Although single-step multiple comparison procedures are utilized in general, the power of these procedures is low for a large number of groups. The closed testing procedures stated in the present paper are more powerful than the single-step procedures. Simulation studies are performed under the null hypothesis and some alternative hypotheses. In this studies, the proposed procedures show a good performance. We also illustrate applying to a dose-finding trial data with unequal sample sizes.

The Japanese Adverse Drug Event Report (JADER) database of the Pharmaceutical and Medical Devices Agency (PMDA) has been available to the public since 2012. The database includes reports on drug-related adverse events from pharmaceutical companies or medical institutions. It is expected to improve the proper use of pharmaceutical products through pharmacoepidemiological studies using the JADER. However, wrong results and interpretations would be derived unless the features of JADER are carefully considered before the study. However, no study has investigated JADER from the viewpoint of data cleaning.

Herein, we summarized the features and precautions for use of JADER (downloaded on June 2015). For example, we found many misspellings and drug names input in various forms because of incorrect Japanese Kanji, voiced and semi-voiced dots, and half-width and full-width forms. We also found that the number of adverse events tends to increase throughout the year, with the highest number reported in the third quarter (October-December). Finally, emergency or rapid safety information (i.e., yellow letter and blue letter) and results of drug use surveys generally increase the number of adverse events reported in JADER.

In this article, we propose an alternative criterion for evaluating parallelism in parallel-line assays at the subject level. Unlike another recently proposed criterion (“ISP”; Uehara et al., 2016), this is a single criterion concerning the quantile of intrasubject slope ratio, which is straightforward to interpret. Two one-sided tolerance limits for a linear combination of the control and test slopes are developed as metrics for the evaluation of discrepancy from the ideal intrasubject parallelism. The proposed metrics are exemplified using data from two ex vivo parallel-line experiments, and their characteristics are investigated through Monte Carlo simulations.