On the bias of order statistics in non-i.i.d. samples
A formula for the leading bias term in the expected value of a central order statistic from a non-i.i.d. sample is derived. This formula generalises the well-known result in the i.i.d. case and covers various situations in which the underlying observations are not independent and/or not identically distributed.
Year of publication: |
1992
|
---|---|
Authors: | Wood, Andrew T. A. |
Published in: |
Statistics & Probability Letters. - Elsevier, ISSN 0167-7152. - Vol. 15.1992, 4, p. 285-291
|
Publisher: |
Elsevier |
Keywords: | Bias Edgeworth expansion (lattice case) i.i.d. order statistics |
Saved in:
Saved in favorites
Similar items by person
-
A multi-dimensional scaling approach to shape analysis
Dryden, Ian L., (2008)
-
Saddlepoint approximations for the Bingham and Fisher–Bingham normalising constants
Kume, A., (2005)
-
Empirical Bayes block shrinkage of wavelet coefficients via the noncentral χ-super-2 distribution
Wang, Xue, (2006)
- More ...