R help - May 2002 - GLM family variance function

Hi

Still strugling with GLMs.

I need to use a different variance function for the gamma family. Has
far has I understand, assuming Y~G(\mu,\nu), the glm function uses
V(\mu)=\mu^2 , but I need to use V(\mu)=\mu^2/\nu. I have a problem of
variance proportional to the mean.

Regards

EJ 





-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
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
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._

On 13 May 2002, Ernesto Jardim wrote:
> Hi
>
> Still strugling with GLMs.
>
> I need to use a different variance function for the gamma family. Has
> far has I understand, assuming Y~G(\mu,\nu), the glm function uses
> V(\mu)=\mu^2 , but I need to use V(\mu)=\mu^2/\nu. I have a problem of
> variance proportional to the mean.
family=quasipoisson() has variance proportional to mean

	-thomas


-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
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
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._