Message-ID: <8E2085D6-14F9-4706-B561-824F9E300135@MUOhio.edu>
Date: 2006-12-20T21:20:52Z
From: Martin Henry H. Stevens
Subject: lme4 mcmcsamp matrix not PD
In-Reply-To: <40e66e0b0612200515h107f6b97k5f7b50384bb1d1db@mail.gmail.com>
Hi folks,
I am not providing a small replicable example, because I assume the
problem is related to my quirky data (~650 obs.).
I am using the latest lme4, matrix and coda, and R 2.4.0.
I frequently get the following error message for this particular lmer
model. I do not get this message for the vast majority of my uses of
mcmcsamp.
I was wondering if it might be characteristic of particular kinds of
problems.
> modb <- lmer(log(basal+1) ~ nutrient*amd + (1|rack) + (1|
gen:amd), data=dat.b2)
> mod.mc <- mcmcsamp(modb, n=10^4)
Error: Matrix is not pd after safe_pd_matrix!
Error in t(.Call(mer_MCMCsamp, object, saveb, n, trans, verbose)) :
error in evaluating the argument 'x' in selecting a method for
function 't'
Cheers,
Hank
Dr. Hank Stevens, Assistant Professor
338 Pearson Hall
Botany Department
Miami University
Oxford, OH 45056
Office: (513) 529-4206
Lab: (513) 529-4262
FAX: (513) 529-4243
http://www.cas.muohio.edu/~stevenmh/
http://www.muohio.edu/ecology/
http://www.muohio.edu/botany/
"E Pluribus Unum"