Which correlation coefficient to take?

Moderators: statman, Analyst Techy, andris, Fierce, GerineL, Smash

rita
Posts: 1
Joined: Sun May 24, 2015 6:17 pm

Which correlation coefficient to take?

Postby rita » Sun May 24, 2015 6:22 pm

Dear all,

I'm a bit confused of those many different correlation coefficients. So I'm not sure what correlation coefficient do I have to use?
I want to find out it the following variables correlate. My variables are:

1)
- Adherence_continuous: continuous but not normally distributed and I dichotomised this continous variable into "adherent" = 0 and "non-adherent" =1.
- Zivil status: it's a categorial variable with 1=married, 2=in a relationship, 3=single 4=divorced and 5=widowed

2)
- Adherence_dichotom: continuous but not normally distributed and I dichotomised this continous variable into "adherent" = 0 and "non-adherent" =1.
- Zivil status: it's a categorial variable with 1=married, 2=in a relationship, 3=single 4=divorced and 5=widowed

Hopefully somebody can help me.

Thanks,
Rita
GerineL
Moderator
Posts: 1477
Joined: Tue Jun 10, 2008 4:50 pm

Re: Which correlation coefficient to take?

Postby GerineL » Mon Jun 01, 2015 9:27 am

basically, if you have 2 nominal variables you need chi square test (via crosstab), but I wonder why you have dichotomized your variable (why would you throw away information if you don't have to?)

Who is online

Users browsing this forum: No registered users and 3 guests

cron