Our World Statistics Day conversations have been a great reminder of how much statistics can inform our lives. Do you have an example of how statistics has made a difference in your life? Share your story with the Community!
Choose Language Hide Translation Bar
Highlighted
Level II

## How do I organize my data in the datasheet to perform a repeated measures test?

I currently am conducting a study in 8 subjects. I continuously measure the subject's heartrate before, during, and after administering a treatment. For each subject, I average the heart rate into two 20 min bins for each section (before/during/after; total 6 bins/subject) and then normalize the bins to the bin immediately before drug administration (Before2). Would a repeated measures test be appropriate for this model? If so, how do I organize the data appropriately in the spreadsheet?

Currently I have the following setup for the data sheet, however, when I perform the repeated measures analysis, the program throws an error (pictured). I am not sure whether it is how I am organizing the table, if I am performing the wrong test, or if I am performing it incorrectly.

1 ACCEPTED SOLUTION

Accepted Solutions
Highlighted
Super User

## Re: How do I organize my data in the datasheet to perform a repeated measures test?

MANOVA is a multivariate method, which implies specifically that there are multiple responses.  I don't think you want to do MANOVA unless I'm missing something.  Your table is structured in the preferred long format already, so there's no problem there.  If you have access to JMP Pro, there is a repeat measures personality in Fit Model that will allow you to specify a correlation structure for Subject.  Without JMP Pro, your best option is probably just make Subject a random variable and Section fixed with a standard least squares personality in Fit Model.

-- Cameron Willden
2 REPLIES 2
Highlighted
Super User

## Re: How do I organize my data in the datasheet to perform a repeated measures test?

MANOVA is a multivariate method, which implies specifically that there are multiple responses.  I don't think you want to do MANOVA unless I'm missing something.  Your table is structured in the preferred long format already, so there's no problem there.  If you have access to JMP Pro, there is a repeat measures personality in Fit Model that will allow you to specify a correlation structure for Subject.  Without JMP Pro, your best option is probably just make Subject a random variable and Section fixed with a standard least squares personality in Fit Model.

-- Cameron Willden
Highlighted
Level II