[R-sig-Geo] Why can you not calculate Moran's i for glm() residuals?

[tara]

Hello Jenn

Unfortunately I can not offer any advice but I am facing very similar
challenges and actively searching for answers. I have presence/absence data
for a colonial species and I am trying to compare the performance of a
logistic model with spatial models: 1) a glm including an autocovariate and
2) a glmm. Currently I have resorted to using spatial correlograms for
visual inspection of residual spatial autocorrelation (interesting that we
both came up with the same posible option). Not ideal and I have not found
any information as to whether this is valid but I am stumped. 
I was wondering if you have found any more information on the topics you
described and if so would you mind sharing what you found with me. I will
certainly return the favour. 

Thanks so much and Good Luck! 

Sincerely 
Tara 
MSc Candidate

-- 
View this message in context: http://r-sig-geo.2731867.n2.nabble.com/Why-can-you-not-calculate-Moran-s-i-for-glm-residuals-tp5568942p5608678.html
Sent from the R-sig-geo mailing list archive at Nabble.com.