The data to be analyzed can be broadly categorized into two types: data collected specifically for analysis and data collected independently of analysis. Analyzing the latter type of data requires various "preprocessing" steps, and the quality of these preprocessing steps significantly impacts the analysis. This study will not deal with the latter type of data.
When data collected for analysis is further classified, one category is data generated through "experiments" in factories and laboratories, and the other is data from daily activities that are not "experiments." The method of statistically analyzing experimental data is known as "experimental design," and by incorporating various ingenious methods at the planning stage, it becomes possible to perform precise analysis with a small number of experiments, i.e., a small amount of data. On the other hand, a representative method for analyzing data from daily activities that are not "experiments" is "multivariate data analysis," and there are various methods for this.
This presentation will introduce a case study in which engineers, particularly young engineers working in a factory, were evaluated by analyzing various data from multiple perspectives using JMP. Since the data was collected during daily activities, the analysis mainly used "multivariate data analysis methods," while also utilizing JMP's powerful exploratory methods.
