R help - May 2004 - lm with predictor matrix

Hello,
  
  can someone give me an example of how to fit a linear model where the
  response is a matrix, please? (other than a loop over lm calls)
  The ?lm points me to model.matrix but it is not clear to me how to use a
  model matrix in an lm call.
 
  fit<-lm(headmatrix ~ tailmatrix) causes problems as soon as I
 use predict(fit,newframe). The variables in tailmatrix are not found in
 newframe.
 
  Thanks,
  
  Claus



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


	[[alternative HTML version deleted]]

Try:

x = matrix(runif(30), 10, 3)
newx = matrix(runif(15), 5, 3)
y = rnorm(10)

fit = lm(y ~ x)
newyhat = predict(fit, newdata=data.frame(x=I(newx)))

HTH,
Andy
> From: Claus Gwiggner
> 
> Hello,
>   
>   can someone give me an example of how to fit a linear model 
> where the
>   response is a matrix, please? (other than a loop over lm calls)
>   The ?lm points me to model.matrix but it is not clear to me 
> how to use a
>   model matrix in an lm call.
>  
>   fit<-lm(headmatrix ~ tailmatrix) causes problems as soon as I
>  use predict(fit,newframe). The variables in tailmatrix are 
> not found in
>  newframe.
>  
>   Thanks,
>   
>   Claus

Your problem might be that the names of 'newframe' don't match 
the column names of 'tailmatrix'.  It's hard to tell because you 
don't provide an example.

Is 'newframe' a matrix or a dataframe?

If it is a dataframe, try:

names(newframe) <- colnames(tailmatrix)

predict(fit, newframe)

-roger

Claus Gwiggner wrote:
> Hello,
>   
>   can someone give me an example of how to fit a linear model where the
>   response is a matrix, please? (other than a loop over lm calls)
>   The ?lm points me to model.matrix but it is not clear to me how to use a
>   model matrix in an lm call.
>  
>   fit<-lm(headmatrix ~ tailmatrix) causes problems as soon as I
>  use predict(fit,newframe). The variables in tailmatrix are not found in
>  newframe.
>  
>   Thanks,
>   
>   Claus
> 
> 
> 
> 		
> ---------------------------------
> 
> 
> 	[[alternative HTML version deleted]]
> 
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://www.stat.math.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide!
http://www.R-project.org/posting-guide.html
>