scholarly journals AJUSTES DE MODELOS VOLUMÉTRICOS PARA O CLONE Eucalyptus grandis x E. urophylla CULTIVADOS NO AGRESTE DE PERNAMBUCO

FLORESTA ◽  
2015 ◽  
Vol 45 (4) ◽  
pp. 663 ◽  
Author(s):  
Francisco Das Chagas Vieira Sales ◽  
José Antonio Aleixo da Silva ◽  
Rinaldo Luiz Caraciolo Ferreira ◽  
Fernando Henrique de Lima Gadelha
Keyword(s):  
Forest Management ◽  
Eucalyptus Grandis ◽  
Symmetric Distributions ◽  
Volumetric Models ◽  
Student T Distribution ◽  
Student Distribution ◽  
T Distribution ◽  
Error Percentage ◽  
Volume Equations ◽  
Eucalyptus Clone

O presente trabalho teve como objetivo avaliar o ajuste de modelos volumétricos para um clone de Eucalyptus usando distribuição normal e t-Student, utilizando dados de um experimento implantado no Instituto Agronômico de Pernambuco (IPA) em São Bento do Una, PE. Para o ajuste dos modelos volumétricos de Silva e Bailey modificado, Chapman e Richard modificado, Schumacher e Hall e, Brody modificado, foram utilizados dados de 62 árvores cubadas rigorosamente pelo método de Smalian. Os critérios usados nas comparações das equações foi o valor ponderado (VP) entre o Índice de Ajuste corrigido (IAc) e o erro percentual absoluto médio (EPAM). De acordo com os resultados o modelo que mostrou melhores ajustes nas duas distribuições foi o de Schumacher e Hall, com melhores ajuste quando da distribuição t-Student. A distribuição t-Student promoveu melhorias nos ajustes das equações em relação à distribuição Normal, quando comparando as duas distribuições em cada equação.AbstractAdjustment of volumetric models for clone of Eucalyptus grandis x E. Urophylla grown on agreste, Pernambuco. This research aimed to evaluate the volumetric models fitting for Eucalyptus clone using normal and t-Student distributions, based on data from an experiment implanted at the Agronomic Institute of Pernambuco (IPA) in São Bento do Una, PE. In order to set the modified volumetric models of Silva and Bailey, modified Chapman and Richard, Schumacher and Hall, and modified Brody, we used data from 62 trees rigorously scaled by Smalian method. The criteria for equation comparing were the weighted value (PV) between the corrected index adjustment (IAc) and absolute mean error percentage (EPAM). According to the results, the model that best fits for the two distributions is Schumacher and Hall, with better adjustment related to the Student-t distribution. The t-Student distribution promoted improvements of equations regarding the Normal distribution, compared to the two distributions per equation.Keywords: Forest management; symmetric distributions; volume equations.

scholarly journals EQUAÇÕES VOLUMÉTRICAS PARA UM CLONE JOVEM DE EUCALIPTO NO SUL DO TOCANTINS

Nativa ◽  
2018 ◽  
Vol 6 ◽  
pp. 795
Author(s):  
Valdir Carlos Lima de Andrade ◽  
Murilo Azevedo Glória Junior ◽  
David Lucas Camargo Vieira Terra
Keyword(s):  
Forest Inventory ◽  
Eucalyptus Grandis ◽  
Single Equation ◽  
Coefficient Of Determination ◽  
Distribution Analysis ◽  
Eucalyptus Urophylla ◽  
Binary Variable ◽  
Volumetric Models ◽  
Eucalyptus Clone ◽  
Diameter Classes

Este trabalho teve como objetivo avaliar um total de 26 modelos volumétricos para um clone do híbrido entre Eucalyptus urophylla e Eucalyptus grandis. Foram utilizados dados da cubagem rigorosa de 25 árvores, distribuídas em cinco classes diamétricas com amplitude de 2 cm cada. Para a avaliação dos modelos volumétricos, adotou-se os critérios: coeficiente de determinação ajustado, erro padrão residual, análise da distribuição de resíduos, soma dos quadrados dos resíduos relativos, erro médio e raiz do quadrado médio. O modelo logarítmo: , um dos mais utilizados no Brasil, teve o oitavo lugar como a melhor colocação dentre os 26 modelos volumétricos avaliados. O modelo que mais se destacou foi:  que, ajustado com a inclusão da variável binária Tx, permitiu o ajuste de uma única equação para quantificar, tanto o volume com casca como sem casca, para o clone estudado. A equação obtida foi: .Palavras-chave: inventário florestal, modelos volumétricos, eucalipto. VOLUMETRIC EQUATIONS FOR A YOUNG EUCALYPTUS CLONE IN THE SOUTH OF TOCANTINS ABSTRACT:This work aimed to evaluate a total of 26 volumetric models for clone of the hybrid between Eucalyptus urophylla and Eucalyptus grandis. We used data from the rigorous cubing of 25 trees distributed in five diameter classes with amplitude of 2 cm each. For the evaluation of the volumetric models, the following criteria were adopted: adjusted coefficient of determination, residual standard error, residue distribution analysis, sum of squares of relative residues, mean error and root mean square. The logarithm model: , one of the most used in Brazil, ranked eighth as the best placement among the 26 volumetric models evaluated. The best that most stood out was: which, adjusted with the inclusion of the binary variable Tx, allowed the adjustment of a single equation to quantify both the shell and shelled volume for the studied clone. The equation obtained was: .Keywords: forest inventory, volumetric models, eucalyptus.

scholarly journals A Robust SMC-PHD Filter for Multi-Target Tracking with Unknown Heavy-Tailed Measurement Noise

Sensors ◽  
2021 ◽  
Vol 21 (11) ◽  
pp. 3611
Author(s):  
Yang Gong ◽  
Chen Cui
Keyword(s):  
Target Tracking ◽  
Sequential Monte Carlo ◽  
Measurement Noise ◽  
Particle Simulation ◽  
Target Number ◽  
Student T Distribution ◽  
Multi Target Tracking ◽  
Heavy Tailed ◽  
Scale Matrix ◽  
T Distribution

In multi-target tracking, the sequential Monte Carlo probability hypothesis density (SMC-PHD) filter is a practical algorithm. Influenced by outliers under unknown heavy-tailed measurement noise, the SMC-PHD filter suffers severe performance degradation. In this paper, a robust SMC-PHD (RSMC-PHD) filter is proposed. In the proposed filter, Student-t distribution is introduced to describe the unknown heavy-tailed measurement noise where the degrees of freedom (DOF) and the scale matrix of the Student-t distribution are respectively modeled as a Gamma distribution and an inverse Wishart distribution. Furthermore, the variational Bayesian (VB) technique is employed to infer the unknown DOF and scale matrix parameters while the recursion estimation framework of the RSMC-PHD filter is derived. In addition, considering that the introduced Student- t distribution might lead to an overestimation of the target number, a strategy is applied to modify the updated weight of each particle. Simulation results demonstrate that the proposed filter is effective with unknown heavy-tailed measurement noise.

scholarly journals Cumulants of Multivariate Symmetric and Skew Symmetric Distributions

Symmetry ◽  
2021 ◽  
Vol 13 (8) ◽  
pp. 1383
Author(s):  
Sreenivasa Rao Jammalamadaka ◽  
Emanuele Taufer ◽  
Gyorgy H. Terdik
Keyword(s):  
Comprehensive Treatment ◽  
Multivariate Distributions ◽  
Symmetric Distributions ◽  
Multivariate T Distribution ◽  
T Distribution ◽  
Multivariate T

This paper provides a systematic and comprehensive treatment for obtaining general expressions of any order, for the moments and cumulants of spherically and elliptically symmetric multivariate distributions; results for the case of multivariate t-distribution and related skew-t distribution are discussed in some detail.

scholarly journals Power Birnbaum-Saunders Student t distribution

2017 ◽  
Vol 35 (1) ◽  
pp. 51-70
Author(s):  
Germán Moreno-Arenas ◽  
◽  
Guillermo Martínez-Flórez ◽  
Heleno Bolfarine ◽  
◽  
...  
Keyword(s):  
Student T Distribution ◽  
T Distribution

JUMP, NON-NORMAL ERROR DISTRIBUTION AND STOCK PRICE VOLATILITY — A NONPARAMETRIC SPECIFICATION TEST

2009 ◽  
Vol 54 (01) ◽  
pp. 101-121
Author(s):  
MOHAMMAD MASUDUR RAHMAN ◽  
LAILA ARJUMAN ARA ◽  
ZHENLONG ZHENG
Keyword(s):  
Stock Price ◽  
Stock Return ◽  
Garch Model ◽  
Price Volatility ◽  
Stock Index ◽  
Specification Test ◽  
Significance Level ◽  
Student T Distribution ◽  
T Distribution ◽  
Distribution Assumption

This paper examines a wide variety of popular volatility models for stock index return, including Random Walk model, Autoregressive model, Generalized Autoregressive Conditional Heteroscedasticity (GARCH) model, and extensive GARCH model, GARCH-jump model with Normal, and Student t-distribution assumption as well as nonparametric specification test of these models. We fit these models to Dhaka stock return index from 20 November 1999 to 9 October 2004. There has been empirical evidence of volatility clustering, alike to findings in previous studies. Each market contains different GARCH models, which fit well. From the estimation, we find that the volatility of the return and the jump probability were significantly higher after 27 November 2001. The model introducing GARCH jump effect with normal and Student t-distribution assumption can better fit the volatility characteristics. We find that RW-GARCH-t, RW-AGARCH-t RW-IGARCH-t and RW-GARCH-M-t can pass the nonparametric specification test at 5% significance level. It is suggested that these four models can capture the main characteristics of Dhaka stock return index.

Local Volume Equations and Tables for two Forest Management Units in Bhutan: An Attempt to Provide FMU Specific Estimate of Timber Volume for Sustainable Forest Management

2020 ◽  
Vol 7 (2) ◽  
pp. 62-74
Author(s):  
Younten Phuntsho ◽  
Lha Tshering ◽  
Dorji Wangdi
Keyword(s):  
Forest Management ◽  
Sustainable Forest Management ◽  
Small Deviation ◽  
Field Work ◽  
Pinus Roxburghii ◽  
Management Units ◽  
Local Volume ◽  
Sample Tree ◽  
Species Specific ◽  
Volume Equations

This study developed tree species specific local volume equations and tables for Lingmethang and Rongmanchu Forest Management Units. The field work was conducted between December, 2019 and January 2020. Data was collected for five species (Schima sp., Ltihocarpus sp., Acrocarpus fraxinifolius, Pinus roxburghii and Castanopsis tribuloides) for Lingmethang FMU and six species (Beilschmedia sp., Persea sp., Quercus sp., Alnus nepalensis, Schima wallichii and Cinnamomum sp.) of trees for Rongmanchu FMU. The height and diameter over bark were measured for every sample trees. Using the height and diameter, volumes for each sample tree was calculated and then the models generated were fitted with a minimum of 32 trees per species, which were destructively felled for the purpose. The models were run in R version 3.4.4. A total of 16 models were fitted and tested for each species. The selected models performed well with small deviation for individual trees.

Sign in / Sign up

Export Citation Format

Share Document