article id 653,
category
Research note
Abstract |
View details
|
Full text in PDF |
Author Info
Partial derivatives of the negative exponential, monomolecular, Mitcherlich, Gompertz, logistic, Chapman-Richards, von Bertalanffy, Weibull and the Richard’s nonlinear growth models are presented. The application of these partial derivatives in estimating the model parameters is illustrated. The parameters are estimated using the Marquardt iterative method of nonlinear regression relating top height to age of Norway spruce (Picea abies L.) from the Bowmont Norway Spruce Thinning Experiment. Formulas that provide good initial values of the parameters are specified. Clear definitions of the parameters of the nonlinear models in the context of the system being modelled are found to be critically important in the process of parameter estimation.
-
Fekedulegn,
Department of Statistics, West Virginia University, Eberly College of Arts and Sciences, P.O. Box 6330, Morgantown, WV26506, USA
E-mail:
fdesta@stat.wvu.edu
-
Mac Siurtain,
University College Dublin, Ireland
E-mail:
mpms@nn.ie
-
Colbert,
USDA Forest Service, Northeastern Research Station, Morgantown, West Virginia
E-mail:
jjc@nn.us