cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 
The Discovery Summit 2025 Call for Content is open! Submit an abstract today to present at our premier analytics conference.
Choose Language Hide Translation Bar
View Original Published Thread

Plotting Correlations using tall vs wide datasets

ndowidar
Level III

I have duplicate measurements that I'd like to plot against each other to check for outliers. My problem is that I have two instances of the same data. So I've labeled one set A & the other B for given metric. In JMP, I can't seem to plot A vs B because they're in the same column. Do I have to label each metric with an A or B to plot them against each other? 
 As an example I attached a simplified dataset. I'd like to make a correlation plot between Set A vs B using a correlation of coverage between the the two. 
 Thanks so much! 

1 ACCEPTED SOLUTION

Accepted Solutions
txnelson
Super User


Re: Plotting Correlations using tall vs wide datasets

Split the data table 

     Tables=>Split

Split on Set

Split Columns on Reads and Coverage

Grouping on ID

 

Then you can easily correlate on the 2 columns created for reads and coverage

 

Look at Response Screening to get your correlations in a data table format

     Analyze=>Screening=>Response Screening

txnelson_0-1741729038819.png

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

Jim

View solution in original post

1 REPLY 1
txnelson
Super User


Re: Plotting Correlations using tall vs wide datasets

Split the data table 

     Tables=>Split

Split on Set

Split Columns on Reads and Coverage

Grouping on ID

 

Then you can easily correlate on the 2 columns created for reads and coverage

 

Look at Response Screening to get your correlations in a data table format

     Analyze=>Screening=>Response Screening

txnelson_0-1741729038819.png

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

Jim