Abstract
In many studies, the questionnaire is a common tool for surveying. There are two kinds of questions designed: single-choice questions and multiple-choice questions. For single-choice questions, the methodology for analyzing it has been provided in the literature. However, the analyses of multiple-choice questions are not established as in depth as those for single-choice questions. Recently, there has been a lot of literature published about testing the marginal independence between two questions involving at least one multiple-choice question. However, another important problem regarding this topic is to rank the responses in a multiple-choice question. The issue is whether there are significant differences in the popularity of particular responses within the same question. In this paper, methodologies for ranking responses are proposed.
Original language | English |
---|---|
Pages (from-to) | 465-474 |
Number of pages | 10 |
Journal | Journal of Applied Statistics |
Volume | 35 |
Issue number | 4 |
DOIs | |
State | Published - Apr 2008 |
Keywords
- Likelihood ratio test
- Multiple-choice question
- Ranking consistency
- Single-choice question
- Survey
- Wald test