Abstract
Chapman-Richards function is used to model growth data of dahurian larch (Larix gmelinii Rupr.) from longitudinal measurements using nonlinear mixed-effects modeling approach. The parameter variation in the model was divided into random effects, fixed effects and variance-covariance structure. The values for fixed effects parameters and the variance-covariance matrix of random effects were estimated using NLME function in S-plus software. Autocorrelation structure was considered for explaining the dependency among multiple measurements within the individuals. Information criterion statistics (AIC, BIC and Likelihood ratio test) are used for comparing different structures of the random effects components. These methods are illustrated using the nonlinear mixed-effects methods in S-Plus software. Results showed that the Chapman-Richards model with three random parameters could typically depict the dahurian larch tree growth in northeastern China. The mixed-effects model provided better performance and more precise estimations than the fixed-effects model.
Highlights
Analysis of repeated measurement data is a recurrent challenge to statisticians engaged in biological and biomedical applications
A nonlinear mixed-effects diameter growth model was developed for dahurian larch in northeastern China
The results showed that the Chapman-Richards model with three random parameters was found to be the best in terms of goodness-of-fit criteria
Summary
Analysis of repeated measurement data is a recurrent challenge to statisticians engaged in biological and biomedical applications. A common type of repeated measurement data is longitudinal data. Longitudinal data can be defined as repeated measurement data where the observations within individuals could not have been randomly assigned to the levels of a treatment of interest. Nonlinear mixed effects models provide a tool for analyzing repeated measurements data and give an unbiased and efficient estimation of the fixed parameters of the model. Nonlinear mixed models improve predictive ability if we are able to predict the value of the random parameters for an unsampled location. This is possible if complementary observations of the dependent variable are available. There has been a great deal of recent interest in mixed effects models for repeated measures data in forestry (Calama and Montero, 2004; Gregoire et al, 1995; Jiang and Li, 2008a, b, c)
Sign-in/Register to view highlights & summary 
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call