cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 
The Discovery Summit 2025 Call for Content is open! Submit an abstract today to present at our premier analytics conference.
Choose Language Hide Translation Bar
View Original Published Thread

Robust regression in JMP

sandychristine
Level I

Hi. I found outliers by detecting Robust Outlier analysis in unidimensional data at a time and Robust Outlier analysis in unidimensional data at a time. I wanna to prevent the influences of outliers in multiple linear regression analysis. Should I perform robust regression analysis? If so, how to do it?

 

Or I can detect Hats, studentized Residuals, or Cooks' D distance? If not so bad result, I can also read Standarded least Squares results. Thanks!

3 REPLIES 3
txnelson
Super User


Re: Robust regression in JMP

I will point you to the Statistics Index.  There you will find pointers to the Help pages for Robust Regression, and also an actual Example of a Robust Regression run in JMP.

     Help=>Statistics Index

txnelson_0-1686056723787.png

 

Jim


Re: Robust regression in JMP

Hi, txnelson,

 

Your insights were invaluable and helped me tremendously in my analysis. Thank you for your time and effort.

However, I have come across a new challenge in my research, and I was hoping you could provide some guidance. In my current study, I am trying to predict a dependent variable using multiple independent variables simultaneously. While I have successfully included these variables in the analysis, I realized that the results only present bivariate relationships and do not report the model fit of the regression.

 

 

sandychristine_1-1686110643031.png

 

 

sandychristine_0-1686110587625.png

 

txnelson
Super User


Re: Robust regression in JMP

For multiple linear analyses you need to look into the Multivariate Platform, or the Fit Model Platform. 

I suggest that you take the time to read the Discovering JMP documentation available under the Help pull down menu.  You may also want to explore the JMP Tutorials.

Jim