Fitting nonlinear autoregressive models to describe coffee seed germination

Ciência Rural

Iábita Fabiana Sousa¹  Johan Eugen Kunzle Neto¹  Joel Augusto Muniz¹  Renato Mendes Guimarães¹  Taciana Villela Savian¹  Fabiana Rezende Muniz¹ 

关键词: growth models;    Autocorrelated errors;    Nonlinear regression;    Germination potential;    Regression and correlation;    modelos de crescimento;    erros autocorrelacionados;    regressão não linear;    potencial de germinação;    regressão e correlação;   

DOI  :  10.1590/0103-8478cr20131341

来源: SciELO

【 摘 要 】

Cumulative germination of coffee has a longitudinal behavior mathematically characterized by a sigmoidal model. In the seed germination evaluation, the study of the germination curve may contribute to better understanding of this process. The aim of this study was to evaluate the goodness of fit of Logistic and Gompertz models, with independent and first-order autoregressive errors structure, AR (1), in the description of coffee (Coffea arabica L.) line Catuai vermelho IAC 99 germination, at five different potential germination. The data used were from an experiment conducted in 2011 at the Seed Analysis Laboratory of the Federal University of Lavras. The Logistic and Gompertz nonlinear models were appropriately adjusted to the percentage germination data. The Gompertz model with first-order autoregressive errors structure was the best to describe the germination process

【 授权许可】

CC BY   
 All the contents of this journal, except where otherwise noted, is licensed under a Creative Commons Attribution License