[R-sig-ME] glmer function in lme4 - false convergence warning message, (Austin, Peter)

[Highland Statistics Ltd]

------------------------------

Message: 6
Date: Sat, 22 Feb 2014 15:51:55 +0000
From: "Austin, Peter" <peter.austin at ices.on.ca>
To: "r-sig-mixed-models at r-project.org"
	<r-sig-mixed-models at r-project.org>
Cc: "Austin, Peter" <peter.austin at ices.on.ca>
Subject: [R-sig-ME] glmer function in lme4 - false convergence warning
	message
Message-ID:
	<9ED811556BF51A4C8E7FD77C5133339B45483532 at ICESMBX2.ices.on.ca>
Content-Type: text/plain; charset="iso-8859-1"

I am writing with a question about a warning message that I received when I used the glmer function to fit a complementary log-log binary regression model that incorporated two different sets of random effects. When running the model, I received the following warning message:

Warning message: In mer_finalize(ans) : false convergence (8).

However, output was produced, including regression coefficients, their associated standard errors, z values, and p-values. From the output, everything looked normal. How should I interpret the warning message, and what actions, if any, should I take?

Thanks very much,

Peter
----



Standardize your continous covariates...most of the times that helps.

Alain Zuur





-- 
Dr. Alain F. Zuur

First author of:
1. Beginner's Guide to GAMM with R (2014).
2. Beginner's Guide to GLM and GLMM with R (2013).
3. Begginner's Guide to GAM with R (2012).
4. Zero Inflated Models and GLMM with R (2012).
5. A Beginner's Guide to R (2009).
6. Mixed effects models and extensions in ecology with R (2009).
7. Analysing Ecological Data (2007).

Highland Statistics Ltd.
9 St Clair Wynd
UK - AB41 6DZ Newburgh
Tel:   0044 1358 788177
Email: highstat at highstat.com
URL:   www.highstat.com