A proposal for guidance on the use of Continuous Models in discrete-data survival
DOI:
https://doi.org/10.35819/remat2020v6i2id3906Keywords:
Survival Analysis, Interval Censoring, Discrete Time Failure, Tied ObservationsAbstract
Discrete models are not popular in survival analysis. This mainly occurs due to the lack of works modeling censored discrete data. Thus, the possibility of analyzing discrete data sets through a continuous model certainly makes this analysis a little easier. In this context, this paper proposes decision guides to help a researcher to decide about the use of a continuous model in the analysis of originally discrete-data survival. These decision guides were obtained through Monte Carlo simulations, considering the sample size, the censored percentages and the proportion of ties observations. The decision guides were applied in three data sets obtained in the literature and which showed a simple way to decide when a continuous model can be considered to modelling discrete data.
Downloads
References
AALEN, O. O. Two examples of modelling heterogeneity in survival analysis. Scandinavian Journal of Statistics, v. 14, n. 1, p. 19-25, 1987.
ALMALKI, S. J.; NADARAJAH, S. A new discrete modified Weibull distribution. IEEE Transactions on Reliability, v. 63, n. 1, p. 68-80, 2014. DOI: https://doi.org/10.1109/TR.2014.2299691.
BAKOUCH, H. S.; JAZI, M. A.; NADARAJAH, S. A new discrete distribution. Statistics: A Journal of Theoretical and Applied Statistics, v. 48, n. 1, p. 200-240, 2014. DOI: https://doi.org/10.1080/02331888.2012.716677.
BIAZATTI, E. C. Modelo de regressão log Weibull com fração de cura para dados. 2017. 60 f. Dissertação (Mestrado em Estatística) – Programa de Pós-Graduação em Estatística, Universidade de Brasília, Brasília/DF, 2017.
CHALITA, L. V. A. S.; COLOSIMO, E. A.; DEMÉTRIO, C. B. G. Likelihood Approximations and discrete models for tied survival data. Communications in Statistics: Theory and Methods, v. 31, n. 7, p. 1215-1229, 2002.
Corrêa, J. B.; Costa, L. O.; Oliveira, N. T.; Lima, W. P.; Sluka, K. A.; Liebano, R. E. Effects of the carrier frequency of interferential current on pain modulation and central hypersensitivity in people with chronic nonspecific low back pain: A randomized placebo-controlled trial. European Journal of Pain, v. 20, n. 10, p. 1653-1666, 2016. DOI: https://doi.org/10.1002/ejp.889.
EFRON, B. Logistic regression, survival analysis and the Kaplan-Meier Curve. Journal of the American Statistical Association, v. 83, n. 402, p. 414-425, 1988. DOI: https://doi.org/10.2307/2288857.
HASHIMOTO, E. M. Modelo de regressão para dados com censura intervalar e dados de sobrevivência grupados. 2008. 121 f. Tese (Doutorado em Estatística e Experimentação Agronômica) – Programa de Pós-Graduação em Estatística e Experimentação Agronômica, Universidade de São Paulo, Piracicaba/SP, 2008.
KAPLAN, E. L.; MEIER, P. Nonparametric estimation from incomplete observations. Journal of the American Statistical Association, v. 53, n. 282, p. 457-481, 1958. DOI: https://doi.org/10.2307/2281868.
NAKAGAWA, T.; OSAKI, S. The discrete Weibull distribution. IEEE Transactions on Reliability, v. 24, n. 5, p. 300-301, 1975. DOI: https://doi.org/10.1109/TR.1975.5214915.
NAKANO, E. Y.; CARRASCO, C. G. Uma avaliação do uso de um modelo contínuo na análise de dados discretos de sobrevivência. TEMA: Tendências em Matemática Aplicada e Computacional, v. 7, n. 1, p. 91-100, 2006.
NEKOUKHOU, V; BIDRAM, H. The exponentiated discrete Weibull distribution. Sort, v. 39, n. 1, p. 127-146, 2015.
RINNE, H. The Weibull distribution: a handbook. Boca Raton: Taylor&Francis, 2008.
SILVA, J. F.; LIEBANO, R. E.; CORRÊA, J. B.; MATSUSHITA, R. Y.; NAKANO, E. Y. Análise do tempo para o alívio da intensidade da dor em pacientes com dor lombar crônica não específica via modelo de riscos proporcionais de Cox. Ciência e Natura, v. 39, n. 2, p. 233-243, 2017. DOI: https://doi.org/10.5902/2179460X24102.
TIETZE, C. Fertility after discontinuation of intrauterine and oral contraception. International Journal of Fertility, v. 13, n. 4, p. 385-389, 1968.
VILA, R.; NAKANO, E. Y.; SAULO, H. Theoretical results on the discrete Weibull distribution of Nakagawa and Osaki. Statistics: A Journal of Theoretical and Applied Statistics, v. 53, n. 2, p. 339-363, 2019. DOI: https://doi.org/10.1080/02331888.2018.1550645.
WEIBULL, W. A statistical distribution function of wide applicability. Journal of Applied Mechanics, v. 18, n. 3, p. 293-297, 1951.
Downloads
Published
Issue
Section
License
Copyright (c) 2020 REMAT: Revista Eletrônica da Matemática
This work is licensed under a Creative Commons Attribution 4.0 International License.
REMAT retains the copyright of published articles, having the right to first publication of the work, mention of first publication in the journal in other published media and distribution of parts or of the work as a whole in order to promote the magazine.
This is an open access journal, which means that all content is available free of charge, at no cost to the user or his institution. Users are permitted to read, download, copy, distribute, print, search or link the full texts of the articles, or use them for any other legal purpose, without requesting prior permission from the magazine or the author. This statement is in accordance with the BOAI definition of open access.