[R] corr.test -- use a different null hypothesis
Dr. Hans Georg Krauthaeuser
Hans-Georg.Krauthaeuser at E-Technik.Uni-Magdeburg.DE
Fri Sep 16 12:05:37 CEST 2005
-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1
First of all, I'm a physicist and therefore I'm not much used to use
statistics. So, please forgive me if this is a FAQ or stupid, but I
failed to find the answer by myself.
I want to use corr.test to test for the correlation of two data sets
(actually I have a lot of data set and perform pairwise testing). But I
wanted to find sets where the correlation is less than a certain limit,
i.e. |r_exp| < r_0. As far as I can see corr.test is designed to work
only for the null hypothesis r_exp = 0. I would need H0 as |r_exp|>= r_0.
Is there any way to specify this null-hypothesis to corr.test ?
Any other idea how to test that hypothesis?
Regards
Hans Georg Krauthaeuser
- --
Otto-von-Guericke-Universitaet Magdeburg
IGET | fon: +49 391 67 12195
Postfach 4120 | fax: +49 391 67 11236
39016 Magdeburg | email: hgk at et.Uni-Magdeburg.DE
Germany | www: www.uni-magdeburg.de/krauthae
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.1 (GNU/Linux)
Comment: Using GnuPG with Thunderbird - http://enigmail.mozdev.org
iD8DBQFDKpjxyoYnJ0CXgngRAgzZAJ0adkXej5BADbEu9tH9GzHg7pzzwQCggmvY
zha4F0DF/pDSk6Tx0z59m30=
=zxkJ
-----END PGP SIGNATURE-----
More information about the R-help
mailing list