Correlation for discrete proportion

This topic has 2 replies, 3 voices, and was last updated 14 years, 10 months ago by Phi coefficient.

Viewing 3 posts - 1 through 3 (of 3 total)

Author

Posts
August 14, 2007 at 2:32 pm #47830

MM
★ 20 Years ★
Participant

@MM Include @MM in your post and this person will
be notified via email.

HI,
I have two proportions (from discrete datasets) CE and XPR.
Pls guide how can I find correlation between these two? Which tests can be used here.
Also, we use jmp in our organization and not Minitab… ;O)
Thanks,
Mohit Mahajan

0

August 16, 2007 at 10:58 am #160013

Prasoon
★ 10 Years ★
Participant

@Prasoon Include @Prasoon in your post and this person will
be notified via email.

Hi Mohit,
Can you describe ur situation little more ? I am not able to understand what type of corelation u r looking for betwen two groups. Do u want to check whether there is a difference between the two ?
Tell us in detail so that we can help u.
Prasoon

0

August 16, 2007 at 2:33 pm #160031

Phi coefficient
★ 10 Years ★
Participant

@Phi-coefficient Include @Phi-coefficient in your post and this person will
be notified via email.

If you can depict your two proportions in a 2×2 table ( I am not sure what your data structure looks like) the Phi coefficient can be used. For the comparsion of chi-squares with tables with varying numbers of cells and sample sizes Cramer’s V is used to approximate a correlation.

0
Author

Posts

Viewing 3 posts - 1 through 3 (of 3 total)

The forum ‘General’ is closed to new topics and replies.