Jen_mp3 at msn.com
Thu Mar 12 22:30:09 CET 2009
No, MANOVA is for Multivariate analysis of variance which is used if there
are multiple responses as well as variables but you just have one response
which is blood pressure. You should just have
model <- lm(BP ~Weight+Height)
If Weight is related to Height only one should be significant so you can
drop it from the model and then use anova again to compare the two models.
The collinearity between Weight and Height is really a separate question and
shouldn't be a problem when fitting a model for BP.
View this message in context: http://www.nabble.com/MANOVA-tp22470559p22485695.html
Sent from the R help mailing list archive at Nabble.com.
More information about the R-help