Stat401BLab5
1 Overview
In this lab you will be introduced to using JMP for multiple linear regression analysis. For
this lab you need to be sitting in front of Windows PC that has JMP.
2 Warm-up Exercise
Multiple Linear Regression is available in JMP using the Fit Model platform. Fit Model is
under Modeling on the JMP Starter and is also available under the Analyze pull-down menu.
This handout illustrates obtaining multiple regression output from JMP’s Fit Model analysis
platform.
In class we introduced the example involving the evaluation of student teachers. The response
variable, Y, is the evaluation score given to the student teacher by an experienced teacher.
The explanatory variables are the scores on four standardized tests. The data is available
on the course web page
www.public.iastate.edu/∼wrstephe/stat401.html
1. Go to the course web page and get the data for the teacher evaluation example into
JMP. The easiest way to do this is to use Mozilla Firefox or Internet Explorer, go to
the course web page and click on the JMP file.
2. In JMP go to Analyze and Fit Model. Cast EVAL into the role of the response variable
Y. Add Test1, Test2, Test3 and Test4 to the Construct Model Effects box. Change the
Emphasis to Minimal Report. Click on Run Model.
3. By right clicking on the Parameter Estimates table you can add Columns that include
the upper and lower 95% confidence interval values.
4. From the red triangle pull down menu next to Response EVAL select Row Diagnostics
- Plot Residual by Predicted. This plot will be used to assess model adequacy and the
equal standard deviation condition.
5. From the same red triangle pull down menu you can Save Columns of
•Predicted Values
•Residuals
•Mean Confidence Interval
•Indiv Confidence Interval