Best way to plot Bivariate for many XY pairs?

klipson — Wed, 16 Nov 2016 16:13:45 GMT

I have a datatable with 30 columns, which are 2 different measured parameters of the same 15 items, with about 500k measurements (rows). I want to plot paramA by paramB as a scatterplot for each item, so I want to specify which columns need to be plotted against each other. I want 15 plots, showing A vs B for each.

This isn't a Matched Pairs analysis, since they're different parameters, but the only way I've been able to figure this out is by using the Bivariate platform and putting in my list of X and Y parameters. However, this generates 225 plots, and I only need 15 of those plots. I'm sure there's a better way to do this, but wanted to know if there's a way built into JMP, or I'll need to write a script?

Re: Best way to plot Bivariate for many XY pairs?

txnelson — Wed, 16 Nov 2016 17:08:32 GMT

All you need to do is to Stack the columns using

Tables==>Stack

Specify that you want do a multiple series stack, and specify 2 in the series

Then select your 30 columns

Once you have the stacked data then do your Fit Y by X on the data columns, and specify to do it By the label column.

topic Best way to plot Bivariate for many XY pairs? in Discussions

Best way to plot Bivariate for many XY pairs?

Re: Best way to plot Bivariate for many XY pairs?