Dear Agus,
I am not aware of an appropriate error variance to assume for the underlying scale
for Poisson data. The mechanism would be the same as for a binomial
variable if a suitable variance was known.
The logit, probit and CompLogLog link functions map binomial proportions onto a scale with variances of pi^2/3, 1 and pi^2/6 respectively.
But I am unaware of anagous results for Poisson link functions.
------------------------
Arthur Gilmour
Retired Principal Research Scientist (Biometrics)
-------------------- m2f --------------------
Sent using Mail2Forum (http://www.mail2forum.com).
Read this topic online here:
http://www.vsni.co.uk/forum/viewtopic.php?p=834#834
-------------------- m2f --------------------
Received on Sat Sep 11 2009 - 09:13:37 EST
This webpage is part of the ASReml-l discussion list archives 2004-2010. More information on ASReml can be found at the VSN website. This discussion list is now deprecated - please use the VSN forum for discussion on ASReml. (These online archives were generated using the hypermail package.)