Keywords
k-sample tests
Double minimum algorithm
Fleming and Harrington family
Curvas de supervivencia
Tests para k-muestras
Algoritmo doble mı́nimo
familia de Fleming y Harrington
How to Cite
Abstract
In this paper, an algorithm for the automatic selection of an adequate test for the survival curves comparison is developed. The introduced procedure is an adaptation of the double minimum algorithm for the bandwidth selection in the smoothed nonparametric k-sample tests. The simulation study which was carried out, suggests us that the proposed method, although never is as good as the best one of the considered tests, is the most regular of them.
References
Harrington D.P.; Fleming, T.R. (1982) “A class of rank test procedures for censored survival data”, Biometrika 69: 553–566.
Letón, E.; Zuluaga, P. (2006) “Cómo elegir el test adecuado para comparar curvas de supervivencia”, Medicina Clínica 127(3): 96–99.
Letón, E.; Zuluaga, P. (2002) “Survival tests for r groups”, Biometrical Journal 44: 15–27.
Martínez–Camblor, P.; Larrañaga, N.; Sarasqueta, C.; Basterretxea, M. (2009) “Esa corporeidad mortal y rosa. Análisis del cáncer de mama en Gipúzkoa en presencia de riesgos competitivos”, por aparecer en Gaceta Sanitaria.
Martínez-Camblor, P. (2008) “Estudio sobre los efectos del parámetro de suavizado en contrastes no-paramétricos para k– Muestras”, Revista Colombiana de Estadística 31(2): 157–168.
Martínez-Camblor, P.; de Uña-Álvarez, J. (2009) “Nonparametric k-sample tests: density functions vs. distribution functions”, Computational Statistics & Data Analysis 53(9): 3344–3357.
R Development Core Team (2006) R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna, Austria. http://www.r-project.org