The details section of the help for lm() suggests the response
should either be a numeric vector or a matrix. And the help for
aov() says:
"Fit an analysis of variance model by a call to 'lm' for each
stratum."
hope this helps,
Chuck Cleland
Michael Friendly wrote:> I'm trying to learn to use manova(), and don't understand why none
of
> the following work:
>
> > data(iris)
> > fit <- manova(~ Species, data=iris)
> Error in lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) :
> incompatible dimensions
> > fit <- manova(iris[,1:4] ~ Species, data=iris)
> Error in model.frame(formula, rownames, variables, varnames, extras,
> extranames, :
> invalid variable type
> >
> > YY <- iris[,1:4]
> > species <- iris[,5]
> > fit <- manova(YY ~ species)
> Error in model.frame(formula, rownames, variables, varnames, extras,
> extranames, :
> invalid variable type
>
> It does work if I coerce YY to a matrix:
>
> > fit <- manova(as.matrix(YY) ~ species)
>
> But, ?manova gives no details, and just points to ?aov which says
>
> aov(formula, data = NULL, projections = FALSE, qr = TRUE,
> contrasts = NULL, ...)
>
> Arguments:
>
> formula: A formula specifying the model.
>
> data: A data frame in which the variables specified in the formula
> will be found. If missing, the variables are searched for in
> the standard way.
> ...
>
> If this is not a bug, perhaps the documentation needs to be clearer.
> The only example for
> manova() is found in ?summary.manova. (It would also help if
> model.frame returned
> something to indicate which variable had an invalid type.)
--
Chuck Cleland, Ph.D.
NDRI, Inc.
71 West 23rd Street, 8th floor
New York, NY 10010
tel: (212) 845-4495 (Tu, Th)
tel: (732) 452-1424 (M, W, F)
fax: (917) 438-0894