[R] Association between discrete and continuous variable
spencer.graves at pdf.com
Mon Jul 12 19:19:07 CEST 2004
My recommendations would depend on the nature of the discrete and
continuous variables. What is the application? Is one variable random
and the other a control variable that might be used to predict? If the
continuous variable is random, what about using the R^2 produced by
"lm"? For the case where the discrete variable is random, I just tried
"www.r-project.org" -> search -> "R site search" for "coefficient of
determination for glm". This produced 4 hits, the first of which (dated
Mon Jul 21 2003) cited 3 papers published between 1991 and 1997.
as you suggest, would be appropriate when you have appropriate models
for the random nature of both variables, separately and together.
More generally, what problem are you trying to solve with this?
Who will use the numbers? How will they use them?
hope this helps. spencer graves
Murray Jorgensen wrote:
> I'm wondering if mutual information al la Cover & Thomas (1991, Ch 2)
> is not the killer association measure for all types of random variables?
> Murray Jorgensen
> PS Yes, this is probably OT!
> Richard A. O'Keefe wrote:
>> What's the reommended way, in R, to determine the strength of
>> association between a discrete variable and a continuous variable?
>> Yes, I have read the manuals, trawled the archives, &c.
>> R-help at stat.math.ethz.ch mailing list
>> PLEASE do read the posting guide!
More information about the R-help