[R] Monotonicity correlation coefficients
Rivera Galicia Luis Felipe
luisf.rivera at uah.es
Wed Mar 6 16:33:31 CET 2002
What I mean is something I found in an paper (Cohen (2000): "Multidimensional Analysis of International Social Indicators - Education, Economy, Media and Demography", Social Indicators Research, 50, pp. 83-106). In this paper, the author mentions (page 89) a "regression-free coefficient of correlation called monotonicity correlation (MONCO)". There must be a statistical package, called HUDAP, which calculates these coefficients (http://help.mscc.huji.ac.il/hudap.html).
The problem is that I wanto to see the mathematical expression that allows you to calculate, because Cohen defines the monotonicity correlation as a coefficient that takes into account the similarity of direction between two variables - in other words, whether both are increasing or decreasing. Amar and Toledano (Amar and Toledano, 1997, "Hudap Manual with Mathematics". The Hebrew University of Jerusalem, Jerusalem) define the monotonicity correlation as: "given two NUMERICAL variables x and y, the weak coefficient of monitonicity tells how much the two variables vary in the same sense. In other words, when x increases, does y increase or not?" Supposely, this enables us to recognize non-linear correlations, which may be more complex but also more common, especially in the social work.
I don't know if this is clear enough, but I think that catching other relationships than linear between numerical variables could be very useful.
Warm regards,
Luis Rivera.
Statistics Department.
Universidad de Alcalá.
-----Mensaje original-----
De: Roger Koenker [mailto:roger at ysidro.econ.uiuc.edu]
Enviado el: mar 05/03/2002 17:33
Para: Rivera Galicia Luis Felipe
CC:
Asunto: Re: [R] Monotonicity correlation coefficients
do you mean something like Kendall's tau or Spearman"s rho? See cor.test.
If this isn't what you want I'd be curious to know what you do have in mind.
url: http://www.econ.uiuc.edu Roger Koenker
email roger at ysidro.econ.uiuc.edu Department of Economics
vox: 217-333-4558 University of Illinois
fax: 217-244-6678 Champaign, IL 61820
On Tue, 5 Mar 2002, Rivera Galicia Luis Felipe wrote:
> Could anyone help me to find the mathematical expression to calculate the monotonicity correlation coefficient between two variables?
>
> Thanks in advance.
>
> Luis Rivera.
> Universidad de Alcalá.
> -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
> r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
> Send "info", "help", or "[un]subscribe"
> (in the "body", not the subject !) To: r-help-request at stat.math.ethz.ch
> _._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._
>
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !) To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._
More information about the R-help
mailing list