GENERALIZED LINEAR MODELS FOR TREE SURVIVAL IN FOREST STANDS

• Autor(a) principal: Fiorentin, Luan Demarco
• Data de Publicação: 2020
• Outros Autores: Bonat, Wagner Hugo, Pelissari, Allan Libanio, Machado, Sebastião do Amaral, Téo, Saulo Jorge, Orso, Gabriel
• Tipo de documento: Artigo
• Idioma: eng
• Título da fonte: Cerne (Online)
• Texto Completo: https://cerne.ufla.br/site/index.php/CERNE/article/view/2199
• topic: Elastic net, Link function, Logistic regression, Ridge regression, Stepwise method.

Quantify the surviving trees in a forest stand and estimating the probability of an individual tree survives to environment conditions are fundamental in forest management planning. Therefore, the main goal of this paper is to estimate the tree survival probability in Pinus taeda stands based on generalized linear models (GLM). The data set was obtained from forest inventories carried out in the Midwest of Santa Catarina State, Brazil. The data analysis combined four strategies for covariate selection with four link functions in the specification of the Bernoulli GLM. We performed strategies for covariate selection along with the standard stepwise procedure, where we considered the elastic net approach, as well as its special cases the lasso and ridge penalization. Our analyses showed that the stepwise procedure combined with the complement log-log link function provide the best fit. The final model is composed by five covariates and presents 81,5% of accuracy given by ROC curve. Finally, we evaluated the fitted model by means of the half-Normal plots and randomized quantile residuals, whose results show evidence of a suitable fit. We suggest the stepwise procedure for selecting covariates for predicting the tree survival probability with complement log-log link function.