Title of article
A general bootstrap algorithm for hypothesis testing
Author/Authors
Jose M. and Martيnez-Camblor، نويسنده , , Pablo and Corral، نويسنده , , Norberto، نويسنده ,
Issue Information
روزنامه با شماره پیاپی سال 2012
Pages
12
From page
589
To page
600
Abstract
The bootstrap is a intensive computer-based method originally mainly devoted to estimate the standard deviations, confidence intervals and bias of the studied statistic. This technique is useful in a wide variety of statistical procedures, however, its use for hypothesis testing, when the data structure is complex, is not straightforward and each case must be particularly treated. A general bootstrap method for hypothesis testing is studied. The considered method preserves the data structure of each group independently and the null hypothesis is only used in order to compute the bootstrap statistic values (not at the resampling, as usual). The asymptotic distribution is developed and several case studies are discussed.
Keywords
Competing risk , Gini index , Survival model , Cumulative incidence function
Journal title
Journal of Statistical Planning and Inference
Serial Year
2012
Journal title
Journal of Statistical Planning and Inference
Record number
2221770
Link To Document