Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: Comparing two different Correlation Coefficents

From   Roger Newson <>
To   "" <>
Subject   Re: st: Comparing two different Correlation Coefficents
Date   Mon, 21 Feb 2011 15:30:22 +0000

To compare Spearman correlation coefficients, you probably have to use the bootstrap (using the -bootstrap- prefix) or the jackknife (using the -jackknife- prefix). However, to compare the Kendall tau-a correlation coefficient between X and Z and the Kendall tau-a coefficient between Y and Z, you can use the -somersd- package, downloadable from SSC, together with -lincom-. As in:

somersd z x y, taua transf(z) tdist
lincom (x-y)/2

The -somersd- package is distributed with a suite of .pdf manuals, which explain the methods in more detail. The on-line help contains references for Stata Journal articles, which can be downloaded from the Stata Journal website at

I hope this helps.

Best wishes


Roger B Newson BSc MSc DPhil
Lecturer in Medical Statistics
Respiratory Epidemiology and Public Health Group
National Heart and Lung Institute
Imperial College London
Royal Brompton Campus
Room 33, Emmanuel Kaye Building
1B Manresa Road
London SW3 6LR
Tel: +44 (0)20 7352 8121 ext 3381
Fax: +44 (0)20 7351 8322
Web page:
Departmental Web page:

Opinions expressed are those of the author, not of the institution.

On 21/02/2011 15:08, Rilke Rainer Michael wrote:
Dear Stata-List,

does anyone know how I compare to correlation coefficients (spearman)
from one sample?

The thing is, that I would like to measure the relationship between lets
say x and z and y and z. After that I would like to test whether this
relationship between both differs significantly. Another way to do this
might be, to ran two similar regression models (reg x z and reg y z) and
compare the two b[z] of both models. Does anyone know how to do this in

Kind Regards,

*   For searches and help try:
*   For searches and help try:

© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index