Visiting Researcher, Department of Business Administration, Faculty of Business Administration, Mejiro University
Takenori Takahashi Visiting Professor, Graduate School of Health Management, Keio University
In recent years, online surveys using the Internet have become popular for various surveys conducted by companies. For example, when conducting a nationwide questionnaire survey of more than 10,000 people, it is effective to use online surveys from the perspective of economy and convenience. In order to minimize the number of questions and create a questionnaire with essential content according to the purpose of the survey, taking into account the budget of the survey and the burden on the respondents, it is desirable to examine the questions based on concept diagrams and fishbone diagrams and conduct a preliminary survey in advance. In addition, in the case of a large-scale online questionnaire survey, the analysis of the acquired data does not end with descriptive statistics, but requires a statistical approach using careful stratification and multivariate analysis. This makes it possible to grasp the actual situation of the survey subjects in detail and derive a rational direction for proposals. In this presentation, we will use a practical example of a large-scale online questionnaire survey. In the case study, we will report on the survey idea, the questionnaire design after advance preparation, effective data acquisition through the preliminary survey and the main survey, and the use of partition analysis and selection-type multi-group principal component regression using JMP and the results.
