On Tue, 2 Nov 2004 sgrabasa at escet.urjc.es wrote:
> I am using the glmmPQL package,
I can find no such package: is this the glmmPQL function in the MASS
package?
> and when I run the program I got the
> following warning messages:
>
> 1: non-integer #successes in a binomial glm! in: eval(expr, envir,
> enclos)
> 2: Singular precision matrix in level -1, block 5
>
> What do thy mean?
The first means what it says: you have specified the binomial glm
incorrectly. Please read the posting guide and remember to send us useful
information about what you were doing.
The second means the model fitting process got stuck, and is more likely
an error message. Given the first, no great surprise.
--
Brian D. Ripley, ripley at stats.ox.ac.uk
Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/
University of Oxford, Tel: +44 1865 272861 (self)
1 South Parks Road, +44 1865 272866 (PA)
Oxford OX1 3TG, UK Fax: +44 1865 272595