Please use this identifier to cite or link to this item: http://repositorio.ufla.br/jspui/handle/1/10872
Title: Regressão não linear multivariada no crescimento do coco variedade anã verde
Authors: Muniz, Joel Augusto
Savian, Taciana Villela
Savian, Taciana Villela
Ferreira, Daniel Furtado
Morais, Augusto Ramalho de
Alvarenga, Ângelo Albérico
Keywords: Modelo de crescimento
Análise de regressão multivariada
Mínimos quadrados
Growth model
Multivariate regression analysis
Least squares
Issue Date: 4-Mar-2016
Publisher: Universidade Federal de Lavras
Citation: PRADO, T. K. L. do. Regressão não linear multivariada no crescimento do coco variedade anã verde. 2016. 62 p. Tese (Doutorado em Estatística e Experimentação Agropecuária)-Universidade Federal de Lavras, Lavras, 2016.
Abstract: The green dwarf coconut palm is a major plant resource of humanity whose operation has evolved in most brazilian states because the commercial interest in coconut juice for fresh consumption and use in potting industry, taking up space on bulky soft drinks market. In commercial plantations for the water market in Brazil dominates the dwarf variety, because of its good performance in terms of yield and quality of coconut water. The nonlinear regression models logistic and gompertz growth in the description of plants and fruits have been used. The objective of this study was to evaluate the fit of nonlinear logistic multivariate models (LL), gompertz (GG) and hybrid (GL and LG) by the method of least squares, structure basis of independent and autoregressive errors of the second order for the residuals, to obtain estimates of the parameters. The multivariate models were adjusted growth data of green dwarf coconut fruit, longitudinal and transverse outer diameter. Choosing the best model was made using the Akaike information criterion corrected coefficient of determination adjusted and residual mean square and all the models showed a good fit and the multivariate model gompertz GG, considering auto regressive structure of the second order, were more adequate to fit the experimental data, resulting in estimates consistent with those reported in the literature. The adjustment procedures regression models were performed by the computer program Statistical Analysis System SAS.
URI: http://repositorio.ufla.br/jspui/handle/1/10872
Appears in Collections:DES - Estatística e Experimentação Agropecuária - Doutorado (Teses)

Files in This Item:
File Description SizeFormat 
TESE_Regressão não linear multivariada no crescimento do coco variedade anã verde.pdf593,31 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.