Dear R users, Thanks for the suggestions on how to work around this. One thing is, I have got the impression from reading Agretsi that structural zeros need to be 'treated differently' to sampling zeros. I have an example of a glm with a poisson distribution that subsets the data to remove the structural zero combinations between between two fixed effects whilst leaving the sampling zeros in place. However this isn't for interactions. Unfortunately I'm not a statistician and I'm new to using R. Is this something that I would also have to try to take into account or I have tied myself in knots due to my extremely limited knowledge? Incidently I don't actually have any sampling zeros in my data set if that makes a difference. Thank you all for your help it's very much appreciated Lydia ------------------------------------------------------------------ This message and attachments are subject to a disclaimer. Please refer to http://www.it.up.ac.za/documentation/governance/disclaimer/ for full details. / Hierdie boodskap en aanhangsels is aan 'n vrywaringsklousule onderhewig. Volledige besonderhede is by http://www.it.up.ac.za/documentation/governance/disclaimer/ beskikbaar.
Structural zeros in lme4
1 message · Lydia Belton