FITTING AND SELECTING TRADITIONAL MODELS FOR TREE’S HEIGHT TIME SERIES DATA
Autor(a) principal: | |
---|---|
Data de Publicação: | 2006 |
Outros Autores: | , , |
Tipo de documento: | Artigo |
Idioma: | por |
Título da fonte: | Ciência Florestal (Online) |
Texto Completo: | https://periodicos.ufsm.br/cienciaflorestal/article/view/1898 |
Resumo: | Mesuring trees' height is very importance for planning forest production. Usually, it is accomplished through samplings due to the size of the populations and the size of the trees themselves. Measurements along time form a time series data with some problems for the adjustment of equations to describe its growth. Several models were developed with that purpose. The equations used in this paper were linear, logarithmic, and non-linear models. The statistics used for comparison of those models were the determination coefficient (R²), Cp of Mallows, Akaike's information criterion (AIC), Schwarz's Bayesian criterion (SBC/BIC), squared mean of residues and the graphic analysis of residues. The objective of this work was to develop an example of adjustment of growth equations for height, to demonstrate which one adapts better to the population data and to determine which selection criteria have more relationship with the better true model. To do so, a sample of 64 trees was used, submitted to the trunk analysis, from a population of 531 trees of Pinus elliottii Engelm. The statistics of the sample were compared to the statistics of the population, demonstrating which model describes better the data of the population. Quality of the adjustment to the population's data of each model was evaluated through the Chi-square test and graphic analysis of residues. The Akaike's information criterion (AIC) was appropriated to select models for the data. The two better equations were h=b0+b1.t+b2.t5 and Chapman-Richards' growth model, which showed no significant differences for the chosen criteria in this study. In this sense, the Akaike's information criterion (AIC) calculated to the sample data showed efficiency as an equations' selection criterion to describe the height of the trees along the time for the population used in this study. The generability, calculated by Qui-square test, in relation to the population, didn't show significant difference between models 3 and 9. Final selection, using the qualitative criteria of connection of the model to the studied process, its interpretability and comprehensibility, determined the choice of the Chapman-Richards' model as the best to describe the height growth for the studied trees. |
id |
UFSM-6_5e02092abb724a0a5a39f6ae4d0b885e |
---|---|
oai_identifier_str |
oai:ojs.pkp.sfu.ca:article/1898 |
network_acronym_str |
UFSM-6 |
network_name_str |
Ciência Florestal (Online) |
repository_id_str |
|
spelling |
FITTING AND SELECTING TRADITIONAL MODELS FOR TREE’S HEIGHT TIME SERIES DATAAjuste e seleção de modelos tradicionais para série temporal de dados de altura de árvores.Pinusheigth growth modelsfittingselecting.Pinusmodelos de crescimento em alturaajusteseleçãoMesuring trees' height is very importance for planning forest production. Usually, it is accomplished through samplings due to the size of the populations and the size of the trees themselves. Measurements along time form a time series data with some problems for the adjustment of equations to describe its growth. Several models were developed with that purpose. The equations used in this paper were linear, logarithmic, and non-linear models. The statistics used for comparison of those models were the determination coefficient (R²), Cp of Mallows, Akaike's information criterion (AIC), Schwarz's Bayesian criterion (SBC/BIC), squared mean of residues and the graphic analysis of residues. The objective of this work was to develop an example of adjustment of growth equations for height, to demonstrate which one adapts better to the population data and to determine which selection criteria have more relationship with the better true model. To do so, a sample of 64 trees was used, submitted to the trunk analysis, from a population of 531 trees of Pinus elliottii Engelm. The statistics of the sample were compared to the statistics of the population, demonstrating which model describes better the data of the population. Quality of the adjustment to the population's data of each model was evaluated through the Chi-square test and graphic analysis of residues. The Akaike's information criterion (AIC) was appropriated to select models for the data. The two better equations were h=b0+b1.t+b2.t5 and Chapman-Richards' growth model, which showed no significant differences for the chosen criteria in this study. In this sense, the Akaike's information criterion (AIC) calculated to the sample data showed efficiency as an equations' selection criterion to describe the height of the trees along the time for the population used in this study. The generability, calculated by Qui-square test, in relation to the population, didn't show significant difference between models 3 and 9. Final selection, using the qualitative criteria of connection of the model to the studied process, its interpretability and comprehensibility, determined the choice of the Chapman-Richards' model as the best to describe the height growth for the studied trees.A medição da altura das árvores é de extrema importância para o planejamento da produção florestal. Geralmente, é realizada por meio de amostragens por causa do tamanho das populações e das próprias árvores. Medições ao longo do tempo formam séries de dados temporais que implicam em certos problemas para o ajuste de equações que descrevam sua evolução. Muitos modelos de equações foram desenvolvidos com essa finalidade, sendo que neste trabalho são utilizados modelos lineares, logarítmicos, não-lineares linearizáveis e não-linearizáveis para descrever a altura ao longo do tempo. As estatísticas utilizadas para comparação entre modelos são o coeficiente de determinação (R²), a estatística Cp de Mallows, o critério de informação de Akaike (Akaike's information criterion - AIC), o quadrado médio dos resíduos (QMres) e a análise gráfica de resíduos. O objetivo deste trabalho foi desenvolver um exemplo de ajustamento de equações de crescimento para altura, verificar quais se adaptam melhor aos dados populacionais e determinar que critérios de seleção, entre os utilizados, têm mais relação com o verdadeiro melhor modelo. Para tanto, foi utilizada uma amostra de 64 árvores, provenientes de uma população de 531 árvores de Pinus elliottii Engelm. Nesse caso, as estatísticas da amostra são comparadas com as estatísticas da população, demonstrando qual modelo descreve melhor os dados da população. A qualidade do ajuste dos dados da população aos estimados por cada modelo foi avaliada pelo teste Qui-Quadrado e análise gráfica dos resíduos. O uso do critério de Akaike (AIC) mostrou-se adequado na seleção de modelos para os dados utilizados. As duas melhores equações foram a equação h = b0 + b1.t + b2.t5 e o modelo de Chapman-Richards, que não apresentaram diferenças significativas entre si para os critérios analizados. Nesse sentido, o critério de Akaike, calculado para os dados amostrais, mostrou-se eficiente como critério de seleção de equações para descrever a altura das árvores ao longo do tempo, para a população utilizada neste estudo. A generabilidade, calculada pelo teste Qui-Quadrado em relação à população, não mostrou diferença significativa entre os modelos 3 e 9. A seleção final, usando-se os critérios qualitativos de ligação do modelo com o processo estudado, sua interpretabilidade e compreensibilidade, determinou a escolha do modelo de Chapman-Richards como o melhor para descrever o crescimento em altura das árvores estudadas.Universidade Federal de Santa Maria2006-06-30info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://periodicos.ufsm.br/cienciaflorestal/article/view/189810.5902/198050981898Ciência Florestal; Vol. 16 No. 2 (2006); 177-199Ciência Florestal; v. 16 n. 2 (2006); 177-1991980-50980103-9954reponame:Ciência Florestal (Online)instname:Universidade Federal de Santa Maria (UFSM)instacron:UFSMporhttps://periodicos.ufsm.br/cienciaflorestal/article/view/1898/1144Floriano, Eduardo PagelMuller, IvanorFinger, César Augusto GuimarãesSchneider, Paulo Renatoinfo:eu-repo/semantics/openAccess2017-05-15T14:22:27Zoai:ojs.pkp.sfu.ca:article/1898Revistahttp://www.ufsm.br/cienciaflorestal/ONGhttps://old.scielo.br/oai/scielo-oai.php||cienciaflorestal@ufsm.br|| cienciaflorestal@gmail.com|| cf@smail.ufsm.br1980-50980103-9954opendoar:2017-05-15T14:22:27Ciência Florestal (Online) - Universidade Federal de Santa Maria (UFSM)false |
dc.title.none.fl_str_mv |
FITTING AND SELECTING TRADITIONAL MODELS FOR TREE’S HEIGHT TIME SERIES DATA Ajuste e seleção de modelos tradicionais para série temporal de dados de altura de árvores. |
title |
FITTING AND SELECTING TRADITIONAL MODELS FOR TREE’S HEIGHT TIME SERIES DATA |
spellingShingle |
FITTING AND SELECTING TRADITIONAL MODELS FOR TREE’S HEIGHT TIME SERIES DATA Floriano, Eduardo Pagel Pinus heigth growth models fitting selecting. Pinus modelos de crescimento em altura ajuste seleção |
title_short |
FITTING AND SELECTING TRADITIONAL MODELS FOR TREE’S HEIGHT TIME SERIES DATA |
title_full |
FITTING AND SELECTING TRADITIONAL MODELS FOR TREE’S HEIGHT TIME SERIES DATA |
title_fullStr |
FITTING AND SELECTING TRADITIONAL MODELS FOR TREE’S HEIGHT TIME SERIES DATA |
title_full_unstemmed |
FITTING AND SELECTING TRADITIONAL MODELS FOR TREE’S HEIGHT TIME SERIES DATA |
title_sort |
FITTING AND SELECTING TRADITIONAL MODELS FOR TREE’S HEIGHT TIME SERIES DATA |
author |
Floriano, Eduardo Pagel |
author_facet |
Floriano, Eduardo Pagel Muller, Ivanor Finger, César Augusto Guimarães Schneider, Paulo Renato |
author_role |
author |
author2 |
Muller, Ivanor Finger, César Augusto Guimarães Schneider, Paulo Renato |
author2_role |
author author author |
dc.contributor.author.fl_str_mv |
Floriano, Eduardo Pagel Muller, Ivanor Finger, César Augusto Guimarães Schneider, Paulo Renato |
dc.subject.por.fl_str_mv |
Pinus heigth growth models fitting selecting. Pinus modelos de crescimento em altura ajuste seleção |
topic |
Pinus heigth growth models fitting selecting. Pinus modelos de crescimento em altura ajuste seleção |
description |
Mesuring trees' height is very importance for planning forest production. Usually, it is accomplished through samplings due to the size of the populations and the size of the trees themselves. Measurements along time form a time series data with some problems for the adjustment of equations to describe its growth. Several models were developed with that purpose. The equations used in this paper were linear, logarithmic, and non-linear models. The statistics used for comparison of those models were the determination coefficient (R²), Cp of Mallows, Akaike's information criterion (AIC), Schwarz's Bayesian criterion (SBC/BIC), squared mean of residues and the graphic analysis of residues. The objective of this work was to develop an example of adjustment of growth equations for height, to demonstrate which one adapts better to the population data and to determine which selection criteria have more relationship with the better true model. To do so, a sample of 64 trees was used, submitted to the trunk analysis, from a population of 531 trees of Pinus elliottii Engelm. The statistics of the sample were compared to the statistics of the population, demonstrating which model describes better the data of the population. Quality of the adjustment to the population's data of each model was evaluated through the Chi-square test and graphic analysis of residues. The Akaike's information criterion (AIC) was appropriated to select models for the data. The two better equations were h=b0+b1.t+b2.t5 and Chapman-Richards' growth model, which showed no significant differences for the chosen criteria in this study. In this sense, the Akaike's information criterion (AIC) calculated to the sample data showed efficiency as an equations' selection criterion to describe the height of the trees along the time for the population used in this study. The generability, calculated by Qui-square test, in relation to the population, didn't show significant difference between models 3 and 9. Final selection, using the qualitative criteria of connection of the model to the studied process, its interpretability and comprehensibility, determined the choice of the Chapman-Richards' model as the best to describe the height growth for the studied trees. |
publishDate |
2006 |
dc.date.none.fl_str_mv |
2006-06-30 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://periodicos.ufsm.br/cienciaflorestal/article/view/1898 10.5902/198050981898 |
url |
https://periodicos.ufsm.br/cienciaflorestal/article/view/1898 |
identifier_str_mv |
10.5902/198050981898 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.none.fl_str_mv |
https://periodicos.ufsm.br/cienciaflorestal/article/view/1898/1144 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Universidade Federal de Santa Maria |
publisher.none.fl_str_mv |
Universidade Federal de Santa Maria |
dc.source.none.fl_str_mv |
Ciência Florestal; Vol. 16 No. 2 (2006); 177-199 Ciência Florestal; v. 16 n. 2 (2006); 177-199 1980-5098 0103-9954 reponame:Ciência Florestal (Online) instname:Universidade Federal de Santa Maria (UFSM) instacron:UFSM |
instname_str |
Universidade Federal de Santa Maria (UFSM) |
instacron_str |
UFSM |
institution |
UFSM |
reponame_str |
Ciência Florestal (Online) |
collection |
Ciência Florestal (Online) |
repository.name.fl_str_mv |
Ciência Florestal (Online) - Universidade Federal de Santa Maria (UFSM) |
repository.mail.fl_str_mv |
||cienciaflorestal@ufsm.br|| cienciaflorestal@gmail.com|| cf@smail.ufsm.br |
_version_ |
1799944127004016640 |