Instantly extract effect sizes, F-ratios, and FDR-adjusted p-values from your models with the Calculate Effects Sizes extension, available now in the JMP Marketplace!
New to JMP? Join us Sept. 23-24 for the Early User Edition of Discovery Summit, tailor-made for new users. Register now for free!
See how to use the JMP Marketplace – Free tools to expand JMP capabilities. Register. July 10, 2 pm US Eastern Time.
I would like to have new column property (or modification to existing one) which would allow me setting upper/lower limits and then all the values outside those limits would be treated as missing values.
I have situations where I have hundreds of measurement columns. In some rows single value might be a failed measurement and to easily exclude it from analysis I have two options:
Exclude whole row, but this will make me loose measurement data from all the good measurements also
Stack the data and handle those situations row by row exclusion. This will make it much more difficult to use some of the JMP platforms, column switcher, data filters and so on.
My suggestion is to add column property which I could use to "exclude" (treat as missing) those values from single column. This way I could fairly easily loop over the data and set my limits. Maybe setting this column property could also be added to Explore Outliers platform.
Hi @jthi, the developer reminded me that you can use the Range Check column property for this. "If you set Range Check on a column, it will turn values outside the range into missing. Unlike the proposed property, this will actually change the values. But since they're failed measurements anyway, would it be sufficient?"
Failed measurements was just an example. More realistic example (for my purposes) would be outliers which I would like to temporarily exclude from wide formatted data. Range Check would work fine if it didn't modify the values in the table, that is a feature I do not want (not a problem with failed measurements, but otherwise it would be).