How to do multivariate comparisons in JMP?

[#1]

I would like to know how to do the following type of comparisons on Multivariate data:

1. Comparison to a standard value

2. Two Sample comparison

3. Paired comparison on multivariate data

I could not see any previous discussion on this topic. Can someone help?

[#2]

I suggest checking out the Fit Y by X platform. Here's an entry point into the large volume of information in the JMP online documentation. You'll need to drill down for the various issues you'd like to explore...but this will get you started:

https://www.jmp.com/support/help/en/15.1/#page/jmp/introduction-to-fit-y-by-x.shtml#

[#3]

To add to Peter...paired comparisons are called "Matched Pairs" in JMP and are under the Analyze>Specialized Models menu. The other two options you are looking for are under the Fit Y by X platform as Peter mentioned.

[#4]

Hi Karen and Peter,

Thanks for your suggestion. But this is not what I am exactly looking for. I am looking for Multivariate comparison which uses Hotelling T Square test. 

Under the ANALYZE > MULTIVARIATE menu there is an option to Hotelling T-square  for One Sample to Standard comparison. So I am now looking for Two Sample Hotelling T-square and Paired Hotelling T-square tests.

Thanks,

SL

[#5]

Hi SL, 

Just curious if you were able to find a way to do a 2-sample Hotelling T2 test comparing 2 populations? I'm interested in the same analysis. Thanks. 

MJZ 

[#6]

If not, I think I may have found a way to use the Manova option under the "Analyze  > Fit Model" menu, though I'm not 100% confident on this. I'm also wondering how to perform the CI's if you get a significant Hotelling's T2 result. 

For those that are interested - I THINK (someone may need to verify) you can use the MANOVA option to perform a 2-sample Hotelling's T2 analysis as follows: 

• Analyze > Fit Model > select all of your response variables you are trying compare between your 2 groups & move them to "Y", select the column containing your labels for your 2 groups select "Add" under 'Construct Model Effects' > select "Manova" from the 'Personality' dropdown menu > Run > under 'Choose Response' menu, select "Identity" > Run. 
• This should output your F-value and probability for your test. 
• I'm not sure how to do the simultaneous or Bonferroni adjusted intervals from here.