Subject: Re: quasi-likelihood in glm (PR#284)
Date: Wed 22 Sep 1999 - 20:38:29 EST
On Wed, 22 Sep 1999 firstname.lastname@example.org wrote:
> I have been using quasi-likelihood to analyze some overdispersed lesion
> count data which requires the variance function "mu^2" (specifically,
> I am using glm with the family quasi(var="mu^2", link="log")). Some of
> the counts are zero which led to problems fitting the model in R.
> 1) glm was unable to find starting values
> 2) after I supplied initial values from the fit of a Poisson
> model, glm could not proceed because the deviance was infinite.
> Splus 5.0 had no problems fitting the model. I was able to
> reproduce the Splus results by editing the quasi() family
> generator and using the unnormalized quasi-likelihood
> - log(mu) - y/mu (*)
> in place of the normalized version
> log(y/mu) - (y - mu)/mu (**)
> Further investigation of Splus shows how it overcomes these
> two problems
> 1) A fudge factor (in this case 0.167) is added to zero observations
> so that they can be used as starting values.
> 2) The contribution to the deviance is (*) for zero observations
> and (**) for the rest.
> I suggest that R also uses this approach for quasi-likelihood
That is not quite what S-PLUS 5.1 and 2000 have: replace
-log(mu) - (y - mu)/mu
That is, the formula is
-log(mu) - (y - mu)/mu + log(y)I(y > 0)
Note that earlier versions of S-PLUS (e.g. 3.4) are plain wrong (and as
I found the bug I know what the replacment is).
Unless there are any objections I will put these fixes in.
-- Brian D. Ripley, email@example.com 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-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: firstname.lastname@example.org _._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._
This archive was generated by hypermail 2b25 : Tue 04 Jan 2000 - 14:16:08 EST