Statistical Modelling 3 (2003), 273290
Generalized linear mixed models for strawberry inflorescence data
Diana J. Cole
Institue of Mathematics and Statistics,
University of Kent,
Canterbury, Kent CT2 7NF,
UK.
eMail: d.j.cole@kent.ac.uk
Byron J.T. Morgan, and Martin S. Ridout
University of Kent,
Canterbury,
UK.
Abstract:
Strawberry inflorescences have a variable branching structure.
This paper demonstrates how the inflorescence structure can be
modelled concisely using binomial logistic generalized linear
mixed models. Many different procedures exist for estimating
the parameters of generalized linear mixed models, including
penalized likelihood, EM, Bayesian techniques, and simulated
maximum likelihood. The main methods are reviewed and compared
for fitting binomial logistic generalized linear mixed models
to strawberry inflorescence data. Simulations matched to the
original data are used to show that a modified EM method due
to Steele (1996) is clearly the best, in terms of speed and
mean-squared-error performance, for data of this kind.
Keywords:
Correlated binomial; Gauss-Hermite quadrature; GLMMs;
Laplace importance sampling; modified EM; penalized likelihood;
random effects; simulated maximum likelihood;
variance components.
Downloads:
MATLAB program for
estimating parameters using the modified EM method (ModifiedEMmethod.m),
example for a strawberry data set (Exampledataset.m), and a MATLAB
program for generating a set of
strawberry data (generatestrawberrydata.m) in
zipped archive.
back