[R] GLM problem

Prof Brian Ripley ripley at stats.ox.ac.uk
Thu Jun 21 18:47:14 CEST 2001

On Thu, 21 Jun 2001, laurans at roazhon wrote:

> When I add the following instruction : make.link(log) I have an error
> that I don't understand.
> model<-glm(spa~an, family=gaussian, make.link(log))
> error in as.vector(x, "double"): cannot coerce to vector)
> If someone can help,  thanks

Something certainly could.  It's the help page which says


    link: character or numeric; one of `"logit"', `"probit"',
          `"cloglog"', `"identity"', `"log"',  `"sqrt"',  `"1/mu^2"',
          `"inverse"', or number, say lambda resulting in power link mu
          ^ lambda.

log is a function: I think you meant make.link("log").  However, that
is not the only error: I believe you meant

model <- glm(spa ~ an, family=gaussian("log"))

The fourth argument of glm is `data'.  (In this case you will get away
with gaussian(log).

Brian D. Ripley,                  ripley at stats.ox.ac.uk
Professor of Applied Statistics,  http://www.stats.ox.ac.uk/~ripley/
University of Oxford,             Tel:  +44 1865 272861 (self)
1 South Parks Road,                     +44 1865 272860 (secr)
Oxford OX1 3TG, UK                Fax:  +44 1865 272595

r-help 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-help-request at stat.math.ethz.ch

More information about the R-help mailing list