Share your ideas for the JMP Scripting Unsession at Discovery Summit by September 17th. We hope to see you there!
Choose Language Hide Translation Bar
Highlighted
DMAC
Level I

This is the too easy challenge: comparing 7 groups with their known population size and their number of survey responses

OK.  I give up...  I love SAS JMP and consider myself intermediate, but now I think I am a beginner....

I need to simply compare a 7 survey groups to their response rate and their know population size.  Of course, I am thinking simple Chi Square, but cannot get it to work for me.  Any wisdom most appreciated

2 REPLIES 2
Highlighted
txnelson
Super User

Re: This is the too easy challenge: comparing 7 groups with their known population size and their number of survey responses

I would divide Survey Responses by Population, to get the percentage of each off the groups responses, and then analyze the differences between the groups from that new column.
Jim
Highlighted
KarenC
Super User

Re: This is the too easy challenge: comparing 7 groups with their known population size and their number of survey responses

You can do as @txnelson suggests to get your rates but it sounds like you want to get to tests of significance...in your data file I added a column of 1/0 where 1 = responds, 0 = no response and then extended your frequency column so it has the counts of responders and non-responders (I used  the right click to get the formula on the fly to calculate the non-response counts and then just pasted them in the correct column). I also had to add the codes so that the  non-response were aligned to the right groups. Once you do that then you can run the fit Y-by-X with the response counts as the frequency and I think you are where you want to be...ChiSquare test. I added the needed script to your data table and also opened ANOMP (analysis of means for proportions) as then it is easy to pick out the different rates.

Article Labels