Questionnaires are important tools for surveying in many studies. In previous studies, analyses of multiple response questions are not as established in depth as those for single response questions. Wang (2008a) proposed several methods for ranking responses in multiple response questions under the frequentist setup. However in many situations, prior information may exist for the ranks of the responses. Therefore, establishing a methodology combining updated survey data and past information for ranking responses is an essential issue in questionnaire data analysis. Based on several Bayesian multiple testing procedures, this study develops the Bayesian ranking methods by controlling the posterior expected false discovery rate. In addition, a simulation study is conducted to compare these approaches and to derive the appropriate rejection region for testing.
Keywords: Multiple testing; Single response question; Multiple response question; False discovery rate
Biography: Hsiuying Wang is a professor at Institute of Statistics, National Chiao Tung University, Taiwan.
Professor Wang's research interest includes interval estimation, applied statistics and bioinformatics.