Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
st: RE: creating combined correlation of dummy (ordered multilevel)
From
Nick Cox <[email protected]>
To
"'[email protected]'" <[email protected]>
Subject
st: RE: creating combined correlation of dummy (ordered multilevel)
Date
Thu, 9 Jun 2011 17:01:34 +0100
A correlation coefficient is only likely to have meaning if the combined variable in question is at least on an ordered scale. Even to calculate a meaningless correlation for a six-category scale you would need to have such a combined variable.
Nick
[email protected]
Stefan Nijssen
I am struggling to find the correlation of various variables to a dummy variable (6level ordered). The problem is that since the dummies appear in the table as six variables, I cannot read a single correlation between the combined dummy and any other variable (see below). Does anyone know how to do this?
Stefan Nijssen
. correlate AAA AA A BBB BB B wc5 MAR COV
(obs=383)
| AAA AA A BBB BB B wc5 MAR COV
-------------+---------------------------------------------------------------------------------
AAA | 1.0000
AA | -0.0303 1.0000
A | -0.0767 -0.1249 1.0000
BBB | -0.1187 -0.1932 -0.4892 1.0000
BB | -0.0559 -0.0909 -0.2302 -0.3563 1.0000
B | -0.0504 -0.0820 -0.2077 -0.3214 -0.1513 1.0000
wc5 | 0.3377 0.1016 0.1805 -0.1683 -0.0769 -0.1032 1.0000
MAR | 0.0030 0.0101 0.0146 0.0449 -0.0136 -0.0807 0.0176 1.0000
COV | 0.3052 0.1377 0.2432 -0.0967 -0.1235 -0.2545 0.2121 0.1220 1.0000
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/