CRAMÉR TYPE LARGE DEVIATIONS FOR TRIMMED
-STATISTICS
Abstract: In this paper, we propose a new approach to the investigation of asymptotic properties
of trimmed
-statistics and we apply it to the Cramér type large deviation problem. Our
results can be compared with those in Callaert et al. (1982) – the first and, as far as we
know, the single article where some results on probabilities of large deviations for the
trimmed
-statistics were obtained, but under some strict and unnatural conditions. Our
approach is to approximate the trimmed
-statistic by a non-trimmed
-statistic (with
smooth weight function) based on Winsorized random variables. Using this method, we
establish the Cramér type large deviation results for the trimmed
-statistics under quite
mild and natural conditions.
2010 AMS Mathematics Subject Classification: Primary: 62G30, 62E20; Secondary:
60F05, 60F10.
Keywords and phrases: Trimmed
-statistics, central limit theorem, large deviations,
moderate deviations.