Distributions and expectations of order statistics for possibly dependent random variables
The class of all possible distribution functions of each order statistic for a sample of possibly dependent, identically distributed random variables is characterized. An effective method of determination of the extreme values for the expectation and variance of an arbitrary Borel function of order statistic is presented and applied for calculating the moments in the case of uniformly distributed random variables.
Year of publication: |
1994
|
---|---|
Authors: | Rychlik, Tomasz |
Published in: |
Journal of Multivariate Analysis. - Elsevier, ISSN 0047-259X. - Vol. 48.1994, 1, p. 31-42
|
Publisher: |
Elsevier |
Keywords: | dependent random variables order statistics expectation variance extreme point Pontryagin's maximum principle |
Saved in:
Saved in favorites
Similar items by person
-
Bounds for expectations of L-estimates
Rychlik, Tomasz, (1998)
-
Error reduction in density estimation under shape restrictions
Rychlik, Tomasz, (1999)
-
Evaluations of quantiles of system lifetime distributions
Rychlik, Tomasz, (2017)
- More ...