• JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
 
  Bookmark and Share
 
 
Doctoral Thesis
DOI
10.11606/T.11.2012.tde-05072012-091519
Document
Author
Full name
Mariana Ragassi Urbano
E-mail
Institute/School/College
Knowledge Area
Date of Defense
Published
Piracicaba, 2012
Supervisor
Committee
Demetrio, Clarice Garcia Borges (President)
Candolo, Cecilia
Costa, Silvano Cesar da
Leandro, Roseli Aparecida
Zocchi, Silvio Sandoval
Title in Portuguese
Modelagem de mortalidade natural e superdispersão em dados entomológicos
Keywords in Portuguese
Análise de dados
Bioensaios
Modelos lineares generalizados
Modelos mistos
Mortalidade natural
Abstract in Portuguese
Para dados provenientes de bioensaios entomol´ogicos, na maioria das vezes, ´e necess´ario levar em considera¸cao a ocorrencia de mortalidade natural e a superdispers ao. Para incorporar a mortalidade natural, pode-se utilizar a f´ormula de Abbott, que associada ao modelo binomial, caracteriza o modelo padrao de mortalidade natural. Modelos padroes de superdispersao incluem os modelos beta-binomial, log´stico normal, misturas discretas e o uso do fator de heterogeneidade. Como alternativa aos modelos padrao de mortalidade natural, e de mortalidade natural com o fator de heterogeneidade, foi desenvolvido o modelo de mortalidade natural com a inclusao de um efeito aleat´orio no preditor linear, para melhor acomodar a superdispersao. Para obter as estimativas dos parametros desse novo modelo, foram usados os algoritmos de Newton Raphson e EM. Para a verifica¸cao dos ajustes dos modelos foram usados gr´aficos semi-normais de probabilidade com envelopes de simula¸cao, e para realizar a compara¸cao entre os modelos foram utilizados o teste da razao de verossimilhan¸cas e o crit´eiro AIC. A seguir, foram calculadas as estimativas das doses efetivas. Os procedimentos foram todos implementados no software R. Como aplica¸cao, foram analisados tres conjuntos de dados, provenientes de ensaios entomol´ogicos. Para os tres conjuntos de dados, concluiu-se que o modelo de mortalidade natural com efeito aleat´orio ´e superior aos procedimentos padroes, geralmente, utilizados.
Title in English
Modelling natural mortality and overdispersion in entomologic data
Keywords in English
Algorithms
Bioassays
Data Analysis
Generalized linear models
Natural mortality
Abstract in English
When fitting dose-response models to entomological data it is often necessary to take account of natural mortality and/or overdispersion. The standard approach to handle natural mortality is to use Abbotts formula, which allows for a constant underlying mortality rate. Standard overdispersion models include beta-binomial models, logistic-normal, discrete mixtures and the use of the heterogeneity factor. We extend the standard natural mortality model and include a random effect to handle the overdispersion. To obtain the parameters estimates of this new model, two algorithms were used: the Newton Raphson and the EM. For the application, were used three data sets. We introduce the likelihood ratio test, effective dose, and simulated envelope for the natural mortality model with a random effect. The procedures are implemented in the R system. For the three the data sets studied, a significant further improvement in the fit is possible by using the random-effect model.
 
WARNING - Viewing this document is conditioned on your acceptance of the following terms of use:
This document is only for private use for research and teaching activities. Reproduction for commercial use is forbidden. This rights cover the whole data about this document as well as its contents. Any uses or copies of this document in whole or in part must include the author's name.
Publishing Date
2012-07-13
 
WARNING: Learn what derived works are clicking here.
All rights of the thesis/dissertation are from the authors
Centro de Informática de São Carlos
Digital Library of Theses and Dissertations of USP. Copyright © 2001-2020. All rights reserved.