Global Polynomial Kernel Hazard Estimation:Ajuste polinomial global para la estimación kernel de la función de riesgo

Autor: Hiabu, Munir, Miranda, Maria Dolores Martínez, Nielsen, Jens Perch, Spreeuw, Jaap, Tanggaard, Carsten, Villegas, Andrés
Jazyk: angličtina
Rok vydání: 2015
Předmět:
Zdroj: Hiabu, M, Miranda, M D M, Nielsen, J P, Spreeuw, J, Tanggaard, C & Villegas, A 2015, ' Global Polynomial Kernel Hazard Estimation : Ajuste polinomial global para la estimación kernel de la función de riesgo ', Revista Colombiana de Estadistica, vol. 38, no. 2, pp. 399-411 . https://doi.org/10.15446/rce.v38n2.51668
DOI: 10.15446/rce.v38n2.51668
Popis: This paper introduces a new bias reducing method for kernel hazard estimation.The method is called global polynomial adjustment (GPA). It isa global correction which is applicable to any kernel hazard estimator. Theestimator works well from a theoretical point of view as it asymptoticallyreduces bias with unchanged variance. A simulation study investigates thefinite-sample properties of GPA. The method is tested on local constant andlocal linear estimators. From the simulation experiment we conclude thatthe global estimator improves the goodness-of-fit. An especially encouragingresult is that the bias-correction works well for small samples, where traditionalbias reduction methods have a tendency to fail.
Databáze: OpenAIRE