cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 
  • Don’t miss your chance to experience Discovery Summit Europe at our best available rate! Early bird registration through 31 Oct.
  • Graph Builder Toolbar streamlines interactive graphing. Creates shortcuts on Report and GraphBuilder Helpers toolbars. Download and install the extension.
  • JMP will suspend normal business operations for our Rest and Recharge Day on Friday, October 2, 2026.
    Regular business hours will resume on Monday, October 5, 2026.

Discussions

Solve problems, and share tips and tricks with other JMP users.
Choose Language Hide Translation Bar
Sherif_96
Level III

Covariate as a designing factors

If I already have an experiment with three inputs, can I add their data as a covariate in the custom design rather than specifying them as discrete or continuous variables and then designing an Experiment based on those three covariates only?
2 REPLIES 2
Victor_G
Super User

Re: Covariate as a designing factors

Hi @Sherif_96,

 

Yes, you can create a datatable with your covariates and list all their possible values.
Then, you can use the platform Custom design, and in the "Covariate / Candidate Runs" panel, click on "Select Covariate Factors" to select the covariate factors from your table : 

Victor_G_0-1718622733509.png

 

Hope this answer will help you,

Victor GUILLER

"It is not unusual for a well-designed experiment to analyze itself" (Box, Hunter and Hunter)
statman
Super User

Re: Covariate as a designing factors

Perhaps you are using another definition for a covariate, but covariates are meant to be measurable, uncontrollable factors in an experiment.  Using covariates in an experiment is a way to handle noise that is measurable in the experiment.  The covariate is a random variable in an otherwise fixed effects model (hence mixed model).  Analysis of the covariate modifies the data to account for the covariate effect before analysis of the fixed effects model is done.  Depending on the size of the experiment, there is a limit to the number of covariates you can account for.

 

Now you can certainly do regression using random variables all you want.

"All models are wrong, some are useful" G.E.P. Box

Recommended Articles