Subscribe Bookmark RSS Feed

Ways to rank continous variable and save the quantile rank to a new column

polebear11280

Community Trekker

Joined:

Oct 1, 2015

Hi there,

Thank you for looking into my question. I am wondering if there is any easy way to save the quantile rank of variable to a new column in JMP. In SPSS, for example, if you want to get a new column of quantile rank of variable, you can use " rank cases" function and SPSS will evenly group rows/records into number of groups you specify and save the numeric value of the group to a new variable.

Some solutions I have found is on community:

https://community.jmp.com/message/42979#42979

https://community.jmp.com/docs/DOC-6081


but they don't come in a very easy way. I would love to know if there is any built-in function that I haven't got to know yet that could enable this. Thank you!

1 ACCEPTED SOLUTION

Accepted Solutions
Jeff_Perkinson

Community Manager

Joined:

Jun 23, 2011

Solution

Additionally, the Distribution platform can Save Level Numbers from the histogram.

10114_JMPScreenSnapz001.png

So, you can use the grabber (hand) tool to adjust the histogram bins to your liking, setting the number and centering of the bins and then choose Save Level Numbers from the hotspot menu.

-Jeff

-Jeff
4 REPLIES
ian_jmp

Staff

Joined:

Jun 23, 2011

'Cols > Utilities > Make Binning Formula', and the associated 'Help' is another option.

Jeff_Perkinson

Community Manager

Joined:

Jun 23, 2011

Solution

Additionally, the Distribution platform can Save Level Numbers from the histogram.

10114_JMPScreenSnapz001.png

So, you can use the grabber (hand) tool to adjust the histogram bins to your liking, setting the number and centering of the bins and then choose Save Level Numbers from the hotspot menu.

-Jeff

-Jeff
polebear11280

Community Trekker

Joined:

Oct 1, 2015

Hi Jeff,

Thank you for your response. I tried this method and it seems JMP will divide the group based on the value of the variable, which will leave the group evenly distributed ( bars are not the same length/height). Say for example, if I have 1000 rows of income data, I want to save the top 250 income records as group1. In JMP, even if I make it to 5 group, as the example I show below, the first group will not have 250 observations.

10119_pastedImage_1.png

Jordan_Hiller

Joined:

Jun 23, 2011

Try this Interactive Binning Add-in: Interactive Binning (V2)