Share your ideas for the JMP Scripting Unsession at Discovery Summit by September 17th. We hope to see you there!
Choose Language Hide Translation Bar
Highlighted
vincem
Level II

RE: how do i Fit a constrained longitudinal data analysis (cLDA) in JMP

Hi there

How do i fit a cLDA in JMP (via FIT command say) with the constraint that the group means are assumed to be equal at baseline (hence the “constrained” in cLDA). Hence if we had a model with Time and their interaction Group:Time as predictors theoretically  this model structure would impose that the group means are equal at baseline (i think?).

 

In cLDA baseline means are constrained to be equal between the randomised groups; a common baseline mean is assumed and fit across randomised groups. Here is the cDLA model fitted in R..hence i am aiming to implement the cDLA model in JMP via FIT command if possible.

 

Using the FIT data~ time+group.time doesn't seem to impose the common baseline mean constraints.

 

Any advice on how to fit such models in JMP will be appreciated.

 

regards Vince

2 REPLIES 2
Highlighted

RE: how do i Fit a constrained longitudinal data analysis (cLDA) in JMP

I am not familiar with this particular model but I believe that generally you should not include the group (categorical) term in the model to force a common intercept (baseline). You can include it in transformations such as cross terms to interaction effects. This form breaks the linear model hierarchy and JMP will complain but it will let you fit this model.

 

  1. Select Analyze > Fit Model.
  2. Select response column and click Y.
  3. Select the group and time columns, click Macros, and select Full Factorial.
  4. Select the group term in the Effects list and click Remove.
  5. Click Run.
  6. Click Continue when JMP raises issue about missing effect.
Learn it once, use it forever!
Highlighted
vincem
Level II

RE: how do i Fit a constrained longitudinal data analysis (cLDA) in JMP

Thanks Mark
Yes I did assume this to be the way to proceed but I don’t think this is correct . If you do a cross tab of group by time of the predicted values we should get equivalent baseline means - however I believe this isn’t the case.
Article Labels

    There are no labels assigned to this post.