Estimation of non-linear growth models by linearization: a simulation study using a Gompertz function

摘要: A method based on Taylor series expansion for estimation of location parameters and variance components non-linear mixed effects models was considered. An attractive property the is opportunity an easily implemented algorithm. Estimation can be done by common methods linear models, thus existing programs used after small modifications. The applicability this algorithm in animal breeding studied with simulation using a Gompertz function growth model pigs. Two data sets were analyzed: full set containing observations from entire growing period, truncated time trajectory animals slaughtered prematurely, which pig breeding. results 50 replicates indicate that linearization approach capable estimating original satisfactorily. However, related to adult weight becomes unstable case set.