Published
Global Polynomial Kernel Hazard Estimation
Ajuste polinomial global para la estimación kernel de la función de riesgo
DOI:
https://doi.org/10.15446/rce.v38n2.51668Keywords:
Kernel Estimation, Hazard Function, Local Linear Estimation, Boundary Kernels, Polynomial Correction (en)Estimación kernel, Funciones de riesgo, Estimación local lineal, Kernels de frontera, Corrección polinomial. (es)
This paper introduces a new bias reducing method for kernel hazard estimation. The method is called global polynomial adjustment (GPA). It is a global correction which is applicable to any kernel hazard estimator. The estimator works well from a theoretical point of view as it asymptotically reduces bias with unchanged variance. A simulation study investigates the finite-sample properties of GPA. The method is tested on local constant and local linear estimators. From the simulation experiment we conclude that the global estimator improves the goodness-of-fit. An especially encouraging result is that the bias-correction works well for small samples, where traditional bias reduction methods have a tendency to fail.
En este artículo se introduce un nuevo método de correción del sesgo para la estimación núcleo de la función de riesgo. El método, denominado ajuste polinomial global (APG), consiste en una corrección global que es aplicable a cualquier tipo de estimador núcleo de la función de riesgo. Se comprueba que APG posee buenas propiedades asintóticas y que consigue reducir el sesgo sin incrementar la varianza. Se realizan estudios de simulación para evaluar las propiedades del APG en muestras finitas. Dichos estudios muestran un buen comportamiento en la práctica del APG. Esto es especialmente alentador dado que para muestras finitas los métodos tradicionales de reducción del sesgo tienden a tener un comportamiento bastante pobre.
References
Andersen, P., Borgan, O., Gill, R. & Keiding, N. (1993), Statistical Models Based on Counting Processes, Springer, New York.
Copas, J. B. (1995), ‘Local likelihood based on kernel censoring’, Journal of the Royal Statistical Society, Series B 57(1), 221–235.
Efron, B. & Tibshirani, R. (1996), ‘Using specially designed exponential families for density estimation’, Annals of Statistics 24(6), 2431–2461.
Eguchi, S. & Copas, J. (1998), ‘A class of local likelihood methods and near-parametric asymptotics’, Journal of the Royal Statistical Society, Series B 60(4), 709–724.
Gámiz Pérez, M. L., Janys, L., Martínez Miranda, M. D. & Nielsen, J. P. (2013), ‘Bandwidth selection in marker dependent kernel hazard estimation’, Computational Statistics & Data Analysis 68, 155–169.
Gámiz Pérez, M. L., Martínez Miranda, M. D. & Nielsen, J. P. (2013), ‘Smoothing survival densities in practice’, Computational Statistics & Data Analysis 58, 368–382.
Hjort, N. L. & Glad, I. K. (1995), ‘Nonparametric density estimation with a parametric start’, Annals of Statistics 23(3), 882–904.
Hjort, N. L. & Jones, M. C. (1996), ‘Locally parametric nonparametric density estimation’, Annals of Statistics 24(4), 1619–1647.
Jones, M. C., Linton, O. B. & Nielsen, J. P. (1995), ‘A simple bias reduction method for density estimation’, Biometrika 82(2), 327–338.
Jones, M. C. & Signorini, D. F. (1999), ‘A comparison of higher-order bias kernel density estimators’, Journal of the American Statistical Association 439, 1063–1073.
Jones, M. C., Signorini, D. F. & Hjort, N. L. (1999), ‘On multiplicative bias correction in kernel density estimation’, Sankhya 61(1), 422–430.
Koul, H. L. & Song, W. (2013), ‘Large sample results for varying kernel regression estimates’, Journal of Nonparametric Statistics 25(4), 829–853.
Lemonte, A., Martínez-Florez, G. & Moreno-Arenas, G. (2014), ‘Multivariate Birnbaum-Saunders distribution: Properties and associated inference’, Journal of Statistical Computation and Simulation 85(2), 374–392.
Loader, C. R. (1996), ‘Local likelihood density estimation’, Annals of Statistics 24(4), 1602–1618.
Martínez-Flórez, G., Moreno-Arenas, G. & Vergara-Cardozo, S. (2013), ‘Properties and inference for proportional hazard models’, Revista Colombiana de Estadística 36(1), 95–114.
Nielsen, J. P. (1998), ‘Multiplicative bias correction in kernel hazard estimation’, Scandinavian Journal of Statistics 25(3), 541–553.
Nielsen, J. P. (2003), ‘Variable bandwidth kernel hazard estimators’, Journal of Nonparametric Statistics 15(3), 355–376.
Nielsen, J. P. & Linton, O. (1995), ‘Kernel estimation in a nonparametric marker dependent hazard model’, Annals of Statistics 23(5), 1735–1748.
Nielsen, J. P. & Tanggaard, C. (2001), ‘Boundary and bias correction in kernel hazard estimation’, Scandinavian Journal of Statistics 28(4), 675–698.
Nielsen, J. P., Tanggaard, C. & Jones, M. C. (2009), ‘Local linear density estimation for filtered survival data’, Statistics 43(2), 167–186.
Otneim, H., Karlsen, H. A. & Tjøstheim, D. (2013), ‘Bias and bandwidth for local likelihood density estimation’, Statistics and Probability Letters 83(4), 1382– 1387.
Ramlau-Hansen, H. (1983), ‘Smoothing counting process intensities by means of kernel functions’, Annals of Statistics 11(2), 453–466.
Salinas, V., Pérez, P., González, E. & Vaquera, H. (2012), ‘Goodness of fit tests for the gumbel distribution with type II right censored data’, Revista Colombiana de Estadística 35(3), 407–424.
Spreeuw, J., Nielsen, J. P. & Jarner, S. F. (2013), ‘A nonparametric visual test of mixed hazard models’, SORT 37(2), 153–174.
Dimensions
PlumX
Article abstract page views
Downloads
How to Cite
License
Copyright (c) 2015 Revista Colombiana de Estadística
This work is licensed under a Creative Commons Attribution 4.0 International License.
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
