cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 
JMP is taking Discovery online, April 16 and 18. Register today and join us for interactive sessions featuring popular presentation topics, networking, and discussions with the experts.
Choose Language Hide Translation Bar
TropicSnow
Level I

Repeated Measures with Time-Course Data

I have a dataset where the output (yield) of three treatments (varieties) was measured over the course of two months. I would like to do a repeated measures analysis on these data using the measurement date (harvest date in my dataset) as the repeated measure. Looking through existing JMP documentation (like this: http://www.jmp.com/support/notes/30/584.html), I do not see how I can run the analysis based on one of my variables. Also, I only have JMP, not JMP Pro. I know that in SAS I could run something like  PROC Mixed repeating on date; is there something similar that I could do in JMP?

 

My sample dataset is attached.

 

1 ACCEPTED SOLUTION

Accepted Solutions

Re: Repeated Measures with Time-Course Data

For reference, I am using the second method that is described in the technical note that your cited because you do not have JMP Pro. I imported the data from the Excel workbook. The data did not require any further change. I set up the model with plot as a nested random effect. The rest of the model included the variety (nominal modeling type) and harvest data (ordinal modeling type) with a crossed term. The variety does not appear to be significant for either response. Many degrees of freedom go to estimating all the harvest data parameters, though. I tried using the continuous modeling type for harvest data but was not successful.

 

I saved the script for the Fit Model launch dialog and for the Fit Least Squares platform. I uploaded this data table for you here.

View solution in original post

1 REPLY 1

Re: Repeated Measures with Time-Course Data

For reference, I am using the second method that is described in the technical note that your cited because you do not have JMP Pro. I imported the data from the Excel workbook. The data did not require any further change. I set up the model with plot as a nested random effect. The rest of the model included the variety (nominal modeling type) and harvest data (ordinal modeling type) with a crossed term. The variety does not appear to be significant for either response. Many degrees of freedom go to estimating all the harvest data parameters, though. I tried using the continuous modeling type for harvest data but was not successful.

 

I saved the script for the Fit Model launch dialog and for the Fit Least Squares platform. I uploaded this data table for you here.