Ajustes de modelos não lineares de efeitos fixos, com ponderação e misto-aplicações

• Autor(a) principal: Carvalho, Lídia Raquel de [UNESP]
• Data de Publicação: 2014
• Outros Autores: Pereira, Glauber Márcio Silveira [UNESP], Silva, Helenice de Oliveira Florentino [UNESP], Mischan, Martha Maria [UNESP], Furtado, Edson Luiz [UNESP]
• Tipo de documento: Artigo
• Idioma: por
• Título da fonte: Repositório Institucional da UNESP
• Texto Completo: http://jaguar.fcav.unesp.br/RME/fasciculos/v32/v32_n2/indice_v32_n2.php; http://hdl.handle.net/11449/140353
• topic: Non-linear models; Mixed effects models; Weighted models; Growth curves; Longitudinal data; Modelos não lineares; Modelos ponderados; Curvas de crescimento; Dados longitudinais

Nonlinear models tend to be used when it is suggested by theoretical considerations or by non-linear behavior. Even when a linear approximation is acceptable, a non-linear model can also be used to obtain a clear understanding of the parameters. The objective of this research was: to study of logistics, Gompertz, von Bertalanffy and Richards functions with adjustments in three structures: the fixed effects model, the weighting and mixed effects model adjusted to data of volume of the trunk of Eucalyptus grandis, from three growing regions belonging to Votorantim Celulose e Papel. The criteria used for the selection of models were: Error mean square, Akaike information criterion, Akaike weight, Schwarz Bayesian Information Criterion, Breusch-Pagan test and squared correlation coefficient. The model with weighting was the most appropriate. In the choice of the best function, Gompertz was the one that proved better, second was Richards.