Publication details

 

Kernel estimates of hazard funcions for carcinoma data sets

Basic information
Original title:Kernel estimates of hazard funcions for carcinoma data sets
Authors:Ivanka Horová, Jiří Zelinka, Marie Budíková
Further information
Citation:HOROVÁ, Ivanka, Jiří ZELINKA a Marie BUDÍKOVÁ. Kernel estimates of hazard funcions for carcinoma data sets. Environmetrics, Chichester: John Wiley & Sons, 2006, roč. 2006, č. 17, s. 239-255. ISSN 1180-4009.Export BibTeX
@article{636058,
author = {Horová, Ivanka and Zelinka, Jiří and Budíková, Marie},
article_location = {Chichester},
article_number = {17},
keywords = {hazard function; kernel estimate; asymptotic optimal estimate; carcinoma data set},
language = {cze},
issn = {1180-4009},
journal = {Environmetrics},
title = {Kernel estimates of hazard funcions for carcinoma data sets},
url = {www.interscience.wiley.com},
volume = {2006},
year = {2006}
}
Original language:Czech
Field:Applied statistics, operation research
WWW:link to a new windowhttp://www.interscience.wiley.com
Type:Article in Periodical
Keywords:hazard function; kernel estimate; asymptotic optimal estimate; carcinoma data set

The present article focuses on kernel estimates of hazard functions and their derivatives. Our approach is based on the model introduced by Műller and Wang (1990). In order to estimate the hazard function in an effective manner and automatic procedure in a paper by Horová et. al. (2002) is applied. The procedure chooses a bandwidth, a kernel and an order of kernel. As a by-product we propose a special procedure for this estimation of the optimal bandwidth. This is applied to the carcinoma data sets kindly provided by the Masaryk Memorial Cancer Institute in Brno. Attention is also paid to the point of the most rapid change of the hazard function.

The present article focuses on kernel estimates of hazard functions and their derivatives. Our approach is based on the model introduced by Műller and Wang (1990). In order to estimate the hazard function in an effective manner and automatic procedure in a paper by Horová et. al. (2002) is applied. The procedure chooses a bandwidth, a kernel and an order of kernel. As a by-product we propose a special procedure for this estimation of the optimal bandwidth. This is applied to the carcinoma data sets kindly provided by the Masaryk Memorial Cancer Institute in Brno. Attention is also paid to the point of the most rapid change of the hazard function

Related projects: