[R-lang] comparing regression coefficients
Lngmyers
lngmyers at ccu.edu.tw
Fri Sep 7 07:09:51 PDT 2007
James S. Adelman wrote:
> If I've understood your question correctly, you are asking about a linear
> regression model with response, say z, and two predictors x and y:
>
> K: z = a + mx + ny + error
>
> and you wish to know whether H0: m=n. If so, anova(lm(z~x+y),lm(z~I(x+y)))
> should be valid under the usual conditions.
Clever. I'll have to think this through a bit more to see if it's doing
what I want (it gives much lower p values than my resampling code, which
may well be flawed anyway). One test I've done is generate 10000 random
data sets, and as expected, your method has around 5% of the samples
showing a significant difference when alpha = 0.05.
Do you have anything to cite for this...?
--
James Myers
Graduate Institute of Linguistics
National Chung Cheng University
168 University Road, Min-Hsiung
Chia-Yi 62102
TAIWAN
Email: Lngmyers at ccu.edu.tw
Web: http://www.ccunix.ccu.edu.tw/~lngmyers/
Phone: 886-5-242-8251
Fax: 886-5-272-1654
More information about the R-lang
mailing list