Title : ( Optimal record-based statistical procedures for the two-parameter exponential distribution )
Authors: Mahdi Doostparast , N. Balakrishnan ,
دانلود فایل برای اعضای دانشگاهAccess to full-text not allowed by authors
Abstract
Let X_1,X_2,X_3, ... be a sequence of continuous random variables. X_k is a lower record value if it is smaller than all preceding values X_1,X_2,...,X_{k-1}. By definition, X_1 is taken as the first lower record value. An analogous definition can be provided for upper record values. Record statistics arise naturally in many practical problems and in applied fields such as weather and sports wherein a particular data point is archived for posterity if it is smaller or larger than all others recorded in the past, but perhaps is not stored so accessibly otherwise. Indeed, data that are not records are sometimes not available at all. In what follows, we mention some practical situations in which the outcomes available for analysis of data are record statistics.
Keywords
, Two, parameter exponential model; Generalized likelihood ratio test; Invariant test; Monotone likelihood ratio; Neyman, Pearson fundamental lemma; Shortest, width confidence interval; Uniformly most powerful test; Unbiased interval.
@article{paperid:1019135,
author = {Doostparast, Mahdi and N. Balakrishnan},
title = {Optimal record-based statistical procedures for the two-parameter exponential distribution},
journal = {Journal of Statistical Computation and Simulation},
year = {2011},
volume = {81},
number = {12},
month = {December},
issn = {0094-9655},
pages = {2003--2019},
numpages = {16},
keywords = {Two-parameter exponential model; Generalized likelihood ratio
test; Invariant test; Monotone likelihood ratio;
Neyman-Pearson fundamental lemma;
Shortest-width confidence interval; Uniformly most powerful test; Unbiased interval.},
}
%0 Journal Article
%T Optimal record-based statistical procedures for the two-parameter exponential distribution
%A Doostparast, Mahdi
%A N. Balakrishnan
%J Journal of Statistical Computation and Simulation
%@ 0094-9655
%D 2011
