Brock,
If your dichotomy is a true dichomotomy (e.g., male and female), then what
you want to compute is a point-biserial correlation coefficient. The
point-biserial correlation is a special case of the pearson correlation
coefficient that applies when one variable is dichotomous and the other is
continuous. You can compute the point biserial correlation using the
regular correlation syntax (e.g. CORR VAR1 WITH VAR2) in SPSS.
On the other hand, if your dichotomous variable represents a continuous
normal variable that has been dichotomized (e.g., high and low anxiety),
then what you want to compute is the biserial correlation. This is not
quite the same as the point-biserial. To compute the biserial correlation,
you can use an SPSS Macro is available from the following site. Follow this
link and download the r_bis macro:
http://www2.jura.uni-hamburg.de/instkrim/kriminologie/Mitarbeiter/Enzmann/Software/Enzmann_Software.html
HTH,
Stephen Brand
For personalized and professional consultation in statistics and research
design, visit
www.statisticsdoc.com
-----Original Message-----
From: SPSSX(r) Discussion [mailto:
[hidden email]]On Behalf Of
[hidden email]
Sent: Thursday, August 10, 2006 8:34 AM
To:
[hidden email]
Subject: Correlation of Continuous and Dichotomous Variable
Hi All,
I have learned that if its possible, it can be done with SPSS. I am
looking to quantify the relationship between some continuous variables and
a dichotomous variable. I was simply looking to run correlations. Is
this possible in SPSS and how would I go about doing it? I have both SPSS
13 and 14.
Many thanks,
Brock
Locked
