[S] c.i. for spearman

Gerd Rippin (rippin@imsd.uni-mainz.de)
Mon, 9 Mar 1998 08:44:55 +0000


Hello Steve,

There's also an easy way to get asymptotic
confidence limits:

Spearman's correlation coefficient results by plugging the
ranks of the two variables into the formula of the "normal"
Pearson correlation coefficient.

Thus, first calculate ranks, second calculate for the ranks
the Pearson correlation coefficient and get by the way the
confidence limits, you're interested in.

Best regards,
Dipl. Stat. Gerd Rippin
Institut fuer Medizinische Statistik und Dokumentation
Johannes-Gutenberg-Universitaet
Langenbeckstr.1
55101 Mainz
Germany
Tel: +49 6131 176708
Fax: +49 6131 172968
Email: rippin@imsd.uni-mainz.de
-----------------------------------------------------------------------
This message was distributed by s-news@wubios.wustl.edu. To unsubscribe
send e-mail to s-news-request@wubios.wustl.edu with the BODY of the
message: unsubscribe s-news