Skip to content

gamm4: predict to reflect random effects?

2 messages · Mollie Brooks, Mark Miller

#
Hi Mark,

Since no one replied to my question, I assume that the answer given by Simon Wood in 2011 is still current. 
http://r.789695.n4.nabble.com/mgcv-gamm-predict-to-reflect-random-s-effects-td3622738.html

As Wood suggests at the link (scroll down), my lab group is using gam() with a spline for the random effect like s(Subject,bs="re")

Cheers,
Mollie
------------------------
Mollie Brooks, PhD
Postdoctoral Researcher, Population Ecology Research Group
Institute of Evolutionary Biology & Environmental Studies, University of Z?rich
http://www.popecol.org/team/mollie-brooks/
2 days later
#
Hi Mollie,

Thanks for the reply, yep I guess for now using gam is the best option of
simple random effects. I am trying to fit a more complex model with nested
random effects and want both slope and intercept to vary -  I'll try using
splines within a GLMM and seeing how that works out!

Cheers,

Mark
On Fri, Oct 10, 2014 at 9:30 PM, Mollie Brooks <mbrooks at ufl.edu> wrote: