With respect to application of the Pearson
correlation ceofficient to dichotomous variates:
Theoretically, the issue lies not with the
mechanics of calculation per se, but rather
inferences you desire to draw from the
coefficient itself once calculated. The standard
inferential statistics (i.e., tests of significance
of the coefficient, conf. intervals around the coef.)
associated with the Pearson coefficient assume
normality in their derivations. This is
obviously a strong assumption with dummy
variables.
In practice, I find the Pearson coefficient tends
towards either 0 or 1 when applied to dummies.
Best Regards,
Rafael
-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of Dr. Stephen
Owusu-Ansah
Sent: Monday, April 18, 2005 8:20 AM
To: [email protected]
Subject: st: Econometrics Theory Questions on Dummies and Correlation
Analysis
Hi:
I have econometric/statistical theory questions about dummy variables and
correlation analysis:
1. Is there any theory that prohibit one from undertaking a correlation
analysis (i.e., correlation matrix) with either with Pearson or Spearman
rank correlation test on variables, which are all dummies?
2. If there is no prohibition, theory wise, can the bivariate correlation
coeficients for the dummy variables be interpreted in the same way as one
would do with continuous variables?
Thanks for your usual cooperation.
Regards,
Stephen
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
