Main Article Content
This paper is aimed at geostatistical models of prediction of the Eucaliptus’ volume. The available characteristics were genetic material (MG), density, dominant height (Hd), and basal area (Ab). Firstly, a model was chosen at the Hd, in which the MG and density were used as covariates. Next, we fitted a model to the Ab, where the Hd was a covariate, as well as the MG and density. Finally, we selected a model to volume, where all the others variables were used as covariates. We fitted the models with OLS, WLS, ML and REML methods. The MSE, the MSA and the AIC criteria were used to evaluate the predictions and to select the models. The WLS method gave the best adjustment to the dominant height, while the REML gave the best adjustment of the models to basal area and volume. The study allows us to verify that the use of a spatial component in the model and the inclusion of covariables at Hd, Ab and volume models improved their fit. As well as the prediction capacity of those variables were improved by using the covariates and spatial component and the improvement was more evident for the volume variable.
How to Cite
PEREIRA, J. C., SCALET, V., & THIERSCH, C. R. (2016). SELECTION AND FIT OF SPATIAL MODELS TO ESTIMATE THE VOLUME IN A Eucalyptus sp PLANTATION. Brazilian Journal of Biometrics, 34(3), 507–521. Retrieved from https://biometria.ufla.br/index.php/BBJ/article/view/199
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).