Our World Statistics Day conversations have been a great reminder of how much statistics can inform our lives. Do you have an example of how statistics has made a difference in your life? Share your story with the Community!
I had the privilege of participating in JMP’s Analytically Speaking series a couple of weeks ago (June 8, 2016). While I was able to answer many questions submitted during the live broadcast, there were additional questions that are answered in this blog post. In addition, look for future blog posts with more details on analysis of means (ANOM).
Anne Milley and I prepare for the live webcast.
Q. Your book on ANOM is mainly based on SAS; do you intend to provide something similar based on JMP?
A. Our book, The Analysis of Means: A Graphical Method for Comparing Means, Rates, and Proportions was written prior to the implementation of ANOM in JMP. It does include an appendix with some SAS code, but otherwise the material is not software-dependent. All of the examples could now easily be reproduced in JMP (the figures would just look like JMP figures rather than SAS figures). We have no plans for an updated volume.
Q. Where do I find the Analysis of Means menu in JMP?
A. Beginning with JMP 9, the ANOM menu is found in the Fit Y by X platform. When X is categorical and Y is continuous, there is an Analysis of Means menu under the red triangle. When both X and Y are categorical, there is an Analysis of Means for Proportions option under the red triangle.
Q. What hardware do you use for your analysis? Specifically, clustering big data sets?
A. I work on a MacBook Pro with 16 GB of RAM. I tend to work with smaller rather than bigger data sets, so I rarely have an issue with computing speed. If I run a simulation that is computationally intensive, then I might let it run while I take a break.
Q. How can analysis of means or JMP be used for analysis of financials in support of audit works?
A. The analysis of means can be used in many different instances. The key is that you have a number of groups and you want to compare the group means, rates or proportions to the overall mean, rate or proportion. In addition, there are ANOM-type procedures to compare the variability across groups (i.e., to test for homogeneity of variance). In your case, perhaps you would use ANOM if you are auditing multiple departments or similar departments across a large company and you are interested in knowing if any one department had a different mean value of some measure or a different rate of some item you are auditing.
Q. How do JMP and model building fit into tools that enable machine learning?
A. Machine learning is one type of model building. JMP has many different modeling capabilities, and JMP Pro has even more. Recently, I have found the Generalized Regression platform (JMP Pro) to be extremely powerful in my model building. I work in areas where it is important not only to build a model for prediction, but also to be able to interpret the factors and their contribution to the model.