Thanks for the responses. I am going to try modelling the binomial data with a covariate representing the previous value and see if that's sufficient. I haven't used INLA, I have some experience with JAGs but not sure where to start with modelling temporal structures there. I need to model both regularly space and regularly spaces correlation. For the gaussian data I have, I am using lme. Is it ok to select temporal correlation strucutres based on AIC between REML models. I am trying a number of correlation structures (e.g. corSpher, corExp, corAR1). Thanks Sam -- View this message in context: http://r-sig-ecology.471788.n2.nabble.com/Binomial-GLMM-or-GAMM-with-random-intercept-and-temporal-correlation-tp7579035p7579046.html Sent from the r-sig-ecology mailing list archive at Nabble.com.
Binomial GLMM or GAMM with random intercept and temporal correlation
2 messages · SamiC, Becker, Benjamin
1 day later
Jay Ver Hoef developed a package: glmmLDTS that I think deals explicitly with all your issues (binomial, random effects, temporal autocorrelation...but not GAMM). see his page and two papers (Note, it only seems to run on < R.3.0): https://sites.google.com/site/jayverhoef/ *Ver Hoef, J.M.*, London, J.M., and Boveng, P.L. 2010. Fast computing of some generalized linear mixed pseudo-models with temporal autocorrelation. *Computational Statistics **25*(1)*: *39 - 55*. * DOI: 10.1007/s00180-009-0160-1 London, J.M., *Ver Hoef, J.M.*, Jeffries, S.J., Lance, M.M., and Boveng, P.L. 2012. Haul-out behavior of harbor seals (Phoca vitulina) in Hood Canal, Washington. *PLoS ONE **7*(6):e38180. doi:10.1371/journal.pone.0038180 Ben Becker, Ph.D. Science Coordinator and Marine Ecologist Pacific Coast Science and Learning Center Point Reyes National Seashore www.sfnps.org/pcslc
On Wed, Sep 3, 2014 at 6:33 AM, SamiC <samantha.cox at plymouth.ac.uk> wrote:
Thanks for the responses. I am going to try modelling the binomial data with a covariate representing the previous value and see if that's sufficient. I haven't used INLA, I have some experience with JAGs but not sure where to start with modelling temporal structures there. I need to model both regularly space and regularly spaces correlation. For the gaussian data I have, I am using lme. Is it ok to select temporal correlation strucutres based on AIC between REML models. I am trying a number of correlation structures (e.g. corSpher, corExp, corAR1). Thanks Sam -- View this message in context: http://r-sig-ecology.471788.n2.nabble.com/Binomial-GLMM-or-GAMM-with-random-intercept-and-temporal-correlation-tp7579035p7579046.html Sent from the r-sig-ecology mailing list archive at Nabble.com.
_______________________________________________ R-sig-ecology mailing list R-sig-ecology at r-project.org https://stat.ethz.ch/mailman/listinfo/r-sig-ecology