• 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
 
 
Master's Dissertation
DOI
https://doi.org/10.11606/D.11.2019.tde-20191218-135028
Document
Author
Full name
José Erivaldo Pereira
E-mail
Institute/School/College
Knowledge Area
Date of Defense
Published
Piracicaba, 1995
Supervisor
Title in Portuguese
Análise de experimentos de captura-recaptura através de modelos log-lineares
Keywords in Portuguese
ANÁLISE DE EXPERIMENTOS
CAPTURA
JACARÉ
MODELOS LOG-LINEARES
POPULAÇÕES ANIMAIS
RECAPTURA
Abstract in Portuguese
Neste trabalho abordamos a análise de experimento de captura-recaptura usando modelos log-lineares. Para muitos modelos uma equivalente exata pode ser demonstrada entre os parâmetros do modelo log-linear e os parâmetros biológicos usuais tal que as estimativas destes são também estimativas de máxima verossimilhança. Os modelos para populações fechadas onde equivalência exata pode ser estabelecida são Mo, Mt, Mb e Mtb de Otis et al. (1978). Para população aberta exata equivalência é disponível com o modelo Jolly-Seber, ou qualquer submodelo obtido pela omissão de nascimento ou morte, ou ainda, especificando probabilidade de captura constante sobre todas, ou qualquer subconjunto de amostras. Um problema no SAS que produz as histórias de captura com respectivas contagens observadas e outro no GLIM que possibilita uma completa análise dos dados sob o modelo Jolly-Seber ou qualquer derivação deste, são apresentados. É discutida a aplicação desta metodologia num conjunto de dados reais de recaptura de jacaré (Caiman crocrodilus Yacare) obtidos no Pantanal da Nhecolândia, Mato Grosso do Sul, com os resultados mostrando que parâmetros de heterogeneidade nas probabilidades de captura dos animais e parâmetros de dependência de armadilha estão em operação na população estudada. Além disso, verificou-se que a densidade estimada para o ano de 1990 é de 50 animais/km2 valor igual ao encontrado por MOURÃO et al. (1994) utilizando o método de levantamento aéreo.
Title in English
Analysis of capture-recapture experiments through log-linear models
Abstract in English
In this research we approached the analysis of capture-recapture experiments using log-linear models. For many models an exact equivalence can be shown between the parameters of the log-linear model and the usual biological parameters, in such a way that estimatives of them are also maximum likelihood estimatives. Models for closed populations in which an exact equivalencecan be established are Mo, Mt, Mb e Mtb from OTIS et al. (1978). For open populations, exact equivalence is available with the Jolly-Seber model, or submodels obtained by omission of birth, death, or even specifying constant probability of capture over all or any subset of samples. A SAS program, which generates the histories of capture with their respective observed countings and another with GLIM which makes possible a complete analysis of the data based on Jolly-Seber model or any derivation of this, are shown. Aplication of this methodology is discussed on a set of real data on recapture of alligator (Caiman crocodilus yacare) observed at Pantanal de Nhecolândia (Nhecolândia swamp), in the state of Mato Grosso do Sul, Brazil, with results showing that heterogeneity parameters on the probabilities of animal capture and parameters of trap-hapiness were in operation in the target population. On the other hand it was estimated the animal density for the year of 1990 that was 50 animal per squared kilometer the same value as the one found by MOURÃO et al. (1994) utilizing aerial survey.
 
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
2019-12-19
 
WARNING: Learn what derived works are clicking here.
All rights of the thesis/dissertation are from the authors
CeTI-SC/STI
Digital Library of Theses and Dissertations of USP. Copyright © 2001-2021. All rights reserved.