R devel - Feb 1998 - linear models

How can I use linear model regression for more than 1 dependent (response)
variable?

In S it is possible to do something like
S> x<-matrix(rnorm(300),100,3)
S> lm(x[,1:2]~x[,3])
to get

----------------------------------------------------------------------

Response: Y1=20
Call:
lm(formula =3D x[, 1:2] ~ x[, 3])

Coefficients:
 (Intercept)     x[, 3]=20
  0.02778965 -0.1081179

Degrees of freedom: 100 total; 98 residual
Residual standard error: 0.8294969=20

Response: Y2=20
Call:
lm(formula =3D x[, 1:2] ~ x[, 3])

Coefficients:
 (Intercept)     x[, 3]=20
  0.08045632 -0.1815675

Degrees of freedom: 100 total; 98 residual
Residual standard error: 1.081359=20

----------------------------------------------------------------------

This is not possible in R:

R> x<-matrix(rnorm(300),100,3)
R> lm(x[,1:2]~x[,3])
Error: dimnames: number of dimensions must equal number of names


	Andreas

************************************************************************
*                          Andreas Weingessel                          *
************************************************************************
* Institut f=FCr Statistik      *                Tel: (+43 1) 58801 4541 *
* Technische Universit=E4t Wien *                Fax: (+43 1)  504 14 98 *
* Wiedner Hauptstr. 8-10/1071 *     Andreas.Weingessel@ci.tuwien.ac.at *
* A-1040 Wien, Austria        * http://www.ci.tuwien.ac.at/~weingessel *
************************************************************************

-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-devel mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To:
r-devel-request@stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._

>>>>> Andreas Weingessel writes:
> How can I use linear model regression for more than 1 dependent (response)
> variable?
> In S it is possible to do something like
S> x<-matrix(rnorm(300),100,3)
S> lm(x[,1:2]~x[,3])
> to get
The problem is the final line

	dimnames(z$effects)[1] <- list(NULL)

in the multivariate version of lm.fit().

I think this used to work for some time, but now does neither in 0.61.1
nor in 0.62.

Could we replace the line by

	rownames(z$effects) <- NULL

?

-k

	

-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-devel mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To:
r-devel-request@stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._