Analyzing nonlinear population dynamics data

作     者：Chan, G Chan, KS Stenseth, NC Lingjaerde, OC 

作者机构：Univ Iowa Dept Stat & Actuarial Sci Iowa City IA 52242 USA Univ Oslo CEES Dept Biol N-0316 Oslo Norway Univ Oslo Dept Informat N-0316 Oslo Norway 

出 版 物：《JOURNAL OF AGRICULTURAL BIOLOGICAL AND ENVIRONMENTAL STATISTICS》 (农业、生物与环境统计学杂志)

年 卷 期：2004年第9卷第2期

页      面：200-215页

核心收录：

学科分类：0710[理学-生物学] 12[管理学] 0202[经济学-应用经济学] 02[经济学] 1203[管理学-农林经济管理] 020205[经济学-产业经济学] 0714[理学-统计学（可授理学、经济学学位）] 

主　　题：blowfly density-dependent density-independent ecology ecotoxicology generalized additive model negative binomial nonlinear time series normal poisson 

摘      要：We consider the problem of analyzing long-term experiments with panels of nonlinear time-series data in the framework of generalized additive models. Our approach is developed for testing and estimating the (partial) common dynamic structure across treatment groups. We illustrate our approach with a detailed analysis of an ecotoxicological experiment on the effect of sublethal doses of a toxic substance (cadmium) on the long-run dynamic structure of the greenbottle blowfly (Lucilia sericata). The general model for the blowfly experiment is a generalized additive model which is derived from a stage-structured ecological model. We discuss the relationship between the components of the generalized additive model and those of the underlying stage-structured model. In particular, our proposed approach casts new insights on the effect of toxic diet on the population dynamic structure of the blowfly.