Level: Beginner
【Presenter】
Tatsuro Yamamoto, Japan Gore GK Statistics
[Announcement summary]
In this announcement. We would like to introduce the "log-linear variance model" that can be used for fitting the JMP model. Normally, homoscedasticity is assumed when performing regression analysis or analysis of variance (general linear model) by fitting a JMP model. However, the data we handle often deviate from this assumption. The log-linear variance model is a very useful method in such cases. As a countermeasure against unequal distribution, several countermeasures such as change of variables are used. On the other hand, JMP's log-linear variance model analyzes the data as it is, analyzes (models) how the factors affect the mean and variation, and simply uses the prediction profile to analyze the results. You can figure it out. We will also introduce examples of our use.
[Presenter Profile]
Graduated from Nagoya Institute of Technology Graduate School of Materials Engineering in March 1994 and got a job at a chemical manufacturer. Until I changed jobs, I specialized in organic synthesis. After changing jobs to Japan Gore GK, he committed to statistics and has been involved in statistical education and consulting for over 20 years. Immediately after I started committing to this work, I met JMP and was convinced that there was no better statistical software for engineers to use. Since then, we have promoted the spread of JMP as a statistical tool used in-house. He has a strong interest in practical statistics and continues to think about how to utilize statistics using JMP in a wide range of fields from research and development to production technology.
