Skip to content

Is it possible to account for temporal autocorrelation in MCMCglmm?

2 messages · David Villegas Ríos, Jarrod Hadfield

#
Dear all,
For a number of individuals, I have measured several behavioral traits in the
wild. Those traits (e.g. home range) can be estimated on different temporal
scales, for example daily, weekly or monthly. I want to estimate repeatability
of those traits, assuming that the daily/weekly/monthly
measurements (averages) represent replicates. I have 3 months (90 days) of
data for  each trait.

I have run a MCMCglmm model and extracted the residuals from it using:

res=data$trait-predict(model, marginal=NULL)

And then run:
acf(res)

And I found significant autocorrelation in lags 1 and 2.

Is there any way to account for this (temporal) autocorrelation in MCMCglmm?

Sorry for this pretty basic questions but I haven't found an answer so far.

Thanks!

David
1 day later
#
Hi David,

Sorry - this is not possible in MCMCglmm (yet).

Cheers,

Jarrod


Quoting David Villegas R?os <chirleu at gmail.com> on Wed, 1 Apr 2015  
14:34:19 +0200: