[R] help with lasso2 package

Berwin A Turlach berwin at maths.uwa.edu.au
Mon Nov 12 04:08:46 CET 2007


G'day Diana,

On Fri,  9 Nov 2007 11:48:15 -0800 (PST)
<dverzi at mail.sdsu.edu> wrote:

> #general least squares model works fine
> 
> glm.F <- glm(modF, data = F2, family = gaussian)

glm() fits generalised linear models which are different from
general(ised) least squares models.  The latter can be fitted with the
function gls() from the nlme package (and, presumably, also with
functions provided by other packages),

> gl1F<-gl1ce(modF, data=F2, family=gaussian)
> 
>   Error in family(family) : link "family" not available for 
>   gaussian family; available links 
>   are 'inverse', 'log', 'identity'
> 
> > gl1F<-gl1ce(modF, data=F2, family=gaussian(link="identity"))
> 
>    Error in eval(expr, envir, enclos) : object "etastart" not
>    found
> 
> Please advise.

Use l1ce().  l1ce() returns what gl1ce() should return for the gaussian
family with identical link.  Similar to the relationship between lm(...)
and glm(..., family=gaussian).

Hope this helps.

Best wishes,

	Berwin

=========================== Full address =============================
Berwin A Turlach                            Tel.: +65 6515 4416 (secr)
Dept of Statistics and Applied Probability        +65 6515 6650 (self)
Faculty of Science                          FAX : +65 6872 3919       
National University of Singapore     
6 Science Drive 2, Blk S16, Level 7          e-mail: statba at nus.edu.sg
Singapore 117546                    http://www.stat.nus.edu.sg/~statba



More information about the R-help mailing list