Facultade de Fisioterapia

Density comparison for independent and right censored samples via kernel smoothing

de Uña-Álvarez, Jacobo; Martínez Camblor, Pablo
Abstract:
In this paper the problem of comparing k density functions from survival data is considered. Two non-parametric tests based on (two different) generalizations of the L1 measure are adapted to the censored context. The asymptotic distribution of the test statistics is derived, and an approximation based on resampling methods is proposed. The relative power of the tests is investigated through a Monte Carlo simulation study. Results suggest that the tests exhibit good power when no one of the survival functions dominates the others, especially when the censoring distribution is the same along the k groups and the censoring percentage is small.
Year:
2013
Type of Publication:
Article
Keywords:
Kernel density estimator; Common area; L1 measure; Censored data; k sample test
Journal:
Computational Statistics
Volume:
28
Pages:
269-288
Month:
February
DOI:
http://dx.doi.org/10.1007/s00180-011-0298-5
Hits: 1473