[R-sig-ME] Problems with warnings

[Mathias Emil Kaae]

To whom it concerns,

I am using the package glmmTMB to fit a mixed model with interactions using the beta-binomial distribution. I am trying to model plant cover data for specific species in a habitat using a randomized block design with five blocks and 16 plots within them. The question is: are this plant species increasing/decreasing its cover within different plots as a result of different treatments?

As I see it, I only get non-significant results (which is fine). However, I do get this warning when using the package glmmTMB:

Warning message:
In getReStruc(reTrms, ss, aa, reXterms, fr) :
AR1 not meaningful with intercept

Should I worry, and how can I solve this?

I have attached the code and a subset of the data.

Mathias Emil Kaae
PhD student, Aarhus University
Institut for Ecoscience
Vejlsøvej 25, 8600 Silkeborg
Mobil nr.: + 45 61 72 14 01
E-mail: mek using bios.au.dk<mailto:mek using bios.au.dk>