Premium
Nonparametric Comparison for Panel Count Data with Unequal Observation Processes
Author(s) -
Zhao Xingqiu,
Sun Jianguo
Publication year - 2011
Publication title -
biometrics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 2.298
H-Index - 130
eISSN - 1541-0420
pISSN - 0006-341X
DOI - 10.1111/j.1541-0420.2010.01504.x
Subject(s) - nonparametric statistics , event (particle physics) , reliability (semiconductor) , count data , monte carlo method , statistics , sample (material) , mathematics , counting process , statistical hypothesis testing , computer science , econometrics , power (physics) , physics , chemistry , chromatography , quantum mechanics , poisson distribution
Summary This article considers nonparametric comparison of several treatment groups based on panel count data, which often occur in, among others, medical follow‐up studies and reliability experiments concerning recurrent events. For the problem, most of the existing procedures require that observation processes are identical across different treatment groups among other requirements. We propose a new class of nonparametric test procedures that allow different observation processes. The new test statistics are constructed based on the integrated weighted differences between the estimated mean functions of the underlying recurrent event processes. The asymptotic distributions of the proposed test statistics are established and their finite‐sample properties are examined through Monte Carlo simulations, which indicate that the proposed approach works well for practical situations. An illustrative example is provided.