Masaru Kawasaki, Visiting Researcher, Faculty of Management, Mejiro University Takenori Takahashi, Visiting Professor, Graduate School of Keio University
In recent years, online surveys using simple questionnaire creation tools have become popular. These tools allow you to create questionnaires intuitively, and also have a convenient function that displays simple graphs of response data in real time. However, in order to make some kind of plan, such as suggestions or improvements, based on the survey results, it is desirable to conduct more detailed analysis.
In this presentation, we will introduce examples of partition analysis, which finds meaningful stratification from survey data, and selective multi-group principal component regression analysis, which can derive the direction of proposals by combining basic multivariate analysis, using JMP 12 (SAS Institute Inc., Cary, NC, USA). Meaningful stratification improves the contribution rate of the model, and the direction of proposals can be visually confirmed by using JMP, which has excellent visualization functions.
In addition, to create a more concrete plan, a questionnaire experiment will be conducted based on the results of the analysis mentioned above. In the analysis of the questionnaire experiment, a satisfaction function will be used to examine measures that maximize satisfaction. During the presentation, this series of methodologies will be applied to a smartphone satisfaction survey example, and explanations will be given while actually operating JMP.
