[R] Defining own variance function / quasi-likelihood in a GLM

Richard Nixon richard.nixon at mrc-bsu.cam.ac.uk
Mon Jul 1 18:28:31 CEST 2002


I've been looking in the on-line manuals and searching past posts but
can't find an answer to this question.

I'd like to define my own variance function in a GLM.
The function glm(formula, family=quasi(var="var function"))
lets me choose from a selection of built in variances, but I want to
define my own function for the variance.

Is there an S-plus "make.family" type function in R, or some such way of
defining your own quasi-likelihoods in terms of the relationship between the
mean and the variance?



Dr. Richard Nixon
MRC Biostatistics Unit, Institute of Public Health,
Robinson Way, Cambridge, CB2 2SR
Tel: +44 (0)1223 330382, Fax: +44 (0)1223 330388

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