The somersd package, downloadable from SSC using the ssc command, can do
rank analyses on clustered data. The parameters estimated can be Somers'
D (the parameter behind the ranksum test), Kendall's tau-a, or median
differences, slopes and ratios. And the package is distributed with a
set of .pdf manuals.
In Stata, to see a description of the -somersd- package, type
ssc describe somersd
And, to install it, type
ssc install somersd, replace
And, to copy the manuals to your local folder, type
net get somersd.pdf
net get censlope.pdf
net get cendif.pdf
I hope this helps.
Roger
Roger B Newson
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
UNITED KINGDOM
Tel: +44 (0)20 7352 8121 ext 3381
Fax: +44 (0)20 7351 8322
Email: [email protected]
Web page: www.imperial.ac.uk/nhli/r.newson/
Departmental Web page:
http://www1.imperial.ac.uk/medicine/about/divisions/nhli/respiration/pop
genetics/reph/
Opinions expressed are those of the author, not of the institution.
-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of Berthold
Hoppe
Sent: 18 July 2008 14:31
To: [email protected]
Cc: Berthold Hoppe
Subject: st: rank-sum test for clustered data
Dear all,
I am interested in performing a non-parametric test like -ranksum-
using clustered data. I have -n- individuals and -a- observations per
individual.
Is there an option for ranksum/nptrend/or a comparable analysis, which
is comparable to -logit x y, cluster(n)-.
Many thanks and best regards,
Berthold
*
* 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/
*
* 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/
