Recursive U-quantiles
作者:
Ola Hössjer,
期刊:
Sequential Analysis
(Taylor Available online 1997)
卷期:
Volume 16,
issue 1
页码: 119-129
ISSN:0747-4946
年代: 1997
DOI:10.1080/07474949708836376
出版商: Marcel Dekker, Inc.
关键词: Asymptotic normality;incomplete designs;on-line estimator;recursive designs;U-statistics
数据来源: Taylor
摘要:
Suppose we have a function h with m arguments and i.i.d. random variableswith marginal distribution F. Let Hrbe the distribution of einf:,...,Xm), m≥ 2. We consider on-line schemes for estimating quantiles of HF. Such an estimator is based on a design Dn, which is a small subset of all n!/(n-m)! possible index vectors I = (il) having distinct entries not exceeding n. When a new observation Xnarrivesnew vectorswithare used to modify the current estimate. When γ → ∞, the asymptotic relative efficiency of the recursive estimator compared to the off-line estimator (U -quantile) tends to one. The on-line estimator is closely related to incomplete U-quantiles (Hössjer, 1996), and it generalizes a recursive quantile estimator considered by Hoist (1987) for m = 1.
点击下载:
PDF (804KB)
返 回