Please use this identifier to cite or link to this item: http://repositorio.ufla.br/jspui/handle/1/46237
Title: Simulação de modelos multiníveis com regressões adaptativas robustas em condições experimentais de armazenamento de cafés especiais em ambientes refrigerados
Authors: Cirilo, Marcelo Ângelo
Freire, Evelise Roman Corbalan Góis
Silva, Fabyano Fonseca e
Silva, Jackelya Araújo da
Keywords: Cafés especiais - Análise sensorial
Café beneficiado
Outliers
Simulações
Specialty coffees
Processed coffe beans
Simulation
Issue Date: 5-May-2021
Publisher: Universidade Federal de Lavras
Citation: MANOEL, I dos S. Simulação de modelos multiníveis com regressões adaptativas robustas em condições experimentais de armazenamento de cafés especiais em ambientes refrigerados. 2021. 49 p. Dissertação (Mestrado em Estatística e Experimentação Agropecuária) – Universidade Federal de Lavras, Lavras, 2021.
Abstract: Numerous factors contribute to the quality of specialty coffees, including storage and refrigeration conditions. In this sense, we can conjecture that the results of sensory evaluations may be corrupted due to measurement errors, mainly when tasters are not trained, causing the appearance of observation outliers. With this motivation, this study aimed to propose simulation scenarios considering parametric values obtained by adjusting a multilevel model incorporating robust adaptive regressions to the presence of outliers in an actual experiment with processed and non-processed coffees stored at different periods and temperatures. In this context, computationally simulated scenarios, in which the errors in the response of the variable sensory score could be made at L = 5 and 10 units, were considered. The proposed methodology to infer simulated sensory scores in an experiment defined by the experimental conditions of storage and refrigerated environments was feasible because it contemplates robust characteristics in samples characterized with up to 30% of outlier observations in the evaluated simulation scenarios.
URI: http://repositorio.ufla.br/jspui/handle/1/46237
Appears in Collections:Estatística e Experimentação Agropecuária - Mestrado (Dissertações)



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.