Use este identificador para citar ou linkar para este item: http://repositorio.ufla.br/jspui/handle/1/32712
Título : Procedure to identify outliers through cumulative distribution of extremes in a gamma response model
Autor: Resende, Mariana
Brighenti, Carla Regina Guimarães
Cirillo, Marcelo Ângelo
Palavras-chave: False negatives
False positives
Mahalanobis distance
Simulation
Publicador: Taylor and Francis Online
Data da publicação: 2017
Referência: RESENDE, M.; BRIGHENTI, C. R. G.; CIRILLO, M. A. Procedure to identify outliers through cumulative distribution of extremes in a gamma response model. Communications in Statistics - Simulation and Computation, [S.l.], v. 46, n. 9, 2017.
Abstract: This work aimed at proposing a procedure based on the cumulative distribution of maximums and minimums to identify outliers in generalized Gamma-response models. In order to validate such method, we used simulations scenarios defined by the combination of different samples, contamination rate and distributions with different degrees of asymmetry. In this context, probabilities related to errors in classification and accuracy were obtained by carrying by Monte Carlo simulations. Using cumulative distribution of extremes to identify outliers in a Gamma-response model is recommended, since it is not likely to present errors and was highly accurate in all assessed scenarios.
URI: https://www.tandfonline.com/doi/abs/10.1080/03610918.2016.1217015
http://repositorio.ufla.br/jspui/handle/1/32712
Idioma: en_US
Aparece nas coleções:DES - Artigos publicados em periódicos

Arquivos associados a este item:
Não existem arquivos associados a este item.


Os itens no repositório estão protegidos por copyright, com todos os direitos reservados, salvo quando é indicado o contrário.