Premium
First Passage Time Models for Prediction of Developmental Stages
Author(s) -
Jensen Jens Erik,
Rudemo Mats
Publication year - 1991
Publication title -
biometrical journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.108
H-Index - 63
eISSN - 1521-4036
pISSN - 0323-3847
DOI - 10.1002/bimj.4710330102
Subject(s) - mathematics , variance (accounting) , statistics , maximum likelihood , normality , likelihood function , accounting , business
The problem of predicting the date of a developmental stage for plants or animals is formulated as a first passage time problem for a random process, e.g. accumulated degree‐days. By a suitable embedding in a continuous time model the likelihood becomes a smooth function of the parameters, which may be estimated by use of the maximum likelihood method. A set of data on waiting times from sowing to heading for spring barley is analysed. For data of this type we suggest models with variance components corresponding to stations and years. Modifications to take into account variables in addition to temperature, e.g. day length, soil properties and variety effects are briefly discussed. The transform both sides technique of C ARROLL and R UPPERT (1984) is used to stabilize the variance and to achieve approximate normality of the residuals.