問卷中單複選題的選項排序方法的探討

Abstract

問卷調查在許多研究中是一個最常用的工具，而複選題是一個最常被設計在問卷中的題型。近年來，許多研究提出了一些方法對於複選題的資料作分析，其中，複選題的選項排序的問題是一個重要且我們感興趣的議題。在本篇文章中，我們應用了Wang (2008)，Wang和Huang (2014) 所提出的檢定方法，以及Hunter DR (2004) 中討論的Bradley-Terry模型並用Minorization–Maximization演算法來對單選題或複選題的選項做排序。我們將這些方法寫成一個R package，而這個package已經被收錄在R 軟體的程式套件，讓使用者們能更方便的用這些方法來對單選題或複選題的選項做排序。

In many studies, the questionnaire is a common tool for surveying. A multiple response question is a commonly-used question designed in a questionnaire. Recently, many methods had been proposed to analyze data of a multiple responses question in the literature. And ranking responses is one of important issues in analyzing data of a multiple responses question. In this thesis, we use the methods in Wang (2008), Wang and Huang (2014) and Bradley-Terry model with MM (Minorization–Maximization) algorithm in Hunter DR (2004) to develop a R package. It can provide a useful and convenient tool to rank responses in a signal response or a multiple response question.