[Date Index] [Thread Index] [Author Index]

Re: Correlating binary variables

• To: mathgroup at smc.vnet.net
• Subject: [mg70308] Re: Correlating binary variables
• From: Bill Rowe <readnewsciv at sbcglobal.net>
• Date: Thu, 12 Oct 2006 05:37:39 -0400 (EDT)

On 10/11/06 at 1:53 AM, micky at hotmail.com (mickey) wrote:


>I have a problem where I am trying to find the correlation between a
>series of binary variables.

>10101000101010010 11010010100101001 01010010100100101

>and so on. What is good way of going about this? Linear regression
>doesnt seem to be that good a way of doing things when both
>variables are binary.

You haven't really defined what you mean by "correlation between 
a series of binary variables" nor have you said anything as to 
what you plan to do with this information.

Possibly a non-parametric measure of correlation such as 
Kendall's tau will do. Take a look at the function 
KendallRankCorrelation in the package Statistics`MultiDescriptiveStatistics.

--
To reply via email subtract one hundred and four