A very flexible hybrid censoring scheme and its Fisher information

Sangun Park, N. Balakrishnan

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Various hybrid censoring schemes, which are mixtures of Type I and Type II censoring schemes, have been suggested for flexibility in termination time and efficiency level. In this paper, we propose a general hybrid censoring scheme to be a censoring scheme with Type I or Type II bounds which provides more flexible termination time and efficiency level. The Type I hybrid censoring scheme can be interpreted as a Type I censoring scheme with a Type II upper bound, while the generalized Type I hybrid censoring can be interpreted as a Type I censoring scheme with Type II lower and upper bounds. The bounds involved in the termination can also be a hybrid. We then show that the unified hybrid censoring scheme of Balakrishnan et al. [Exact likelihood inference based on an unified hybrid censored sample from the exponential distribution, J. Statist. Comput. Simul. 78 (2008), pp. 475-488] is a special case of the general hybrid censoring scheme. Finally, we discuss several new hybrid censoring schemes and evaluate the Fisher information contained in them.

Original languageEnglish
Pages (from-to)41-50
Number of pages10
JournalJournal of Statistical Computation and Simulation
Volume82
Issue number1
DOIs
Publication statusPublished - 2012 Jan 1

Fingerprint

Fisher Information
Censoring
Type I Censoring
Termination
Fisher information
Type II Censoring
Exact Inference
Censored Samples
Likelihood Inference
Exponential distribution
Upper and Lower Bounds
Flexibility
Upper bound

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Modelling and Simulation
  • Statistics, Probability and Uncertainty
  • Applied Mathematics

Cite this

@article{3435aae84f7646e394e04edb7ccb2bb1,
title = "A very flexible hybrid censoring scheme and its Fisher information",
abstract = "Various hybrid censoring schemes, which are mixtures of Type I and Type II censoring schemes, have been suggested for flexibility in termination time and efficiency level. In this paper, we propose a general hybrid censoring scheme to be a censoring scheme with Type I or Type II bounds which provides more flexible termination time and efficiency level. The Type I hybrid censoring scheme can be interpreted as a Type I censoring scheme with a Type II upper bound, while the generalized Type I hybrid censoring can be interpreted as a Type I censoring scheme with Type II lower and upper bounds. The bounds involved in the termination can also be a hybrid. We then show that the unified hybrid censoring scheme of Balakrishnan et al. [Exact likelihood inference based on an unified hybrid censored sample from the exponential distribution, J. Statist. Comput. Simul. 78 (2008), pp. 475-488] is a special case of the general hybrid censoring scheme. Finally, we discuss several new hybrid censoring schemes and evaluate the Fisher information contained in them.",
author = "Sangun Park and N. Balakrishnan",
year = "2012",
month = "1",
day = "1",
doi = "10.1080/00949655.2010.521503",
language = "English",
volume = "82",
pages = "41--50",
journal = "Journal of Statistical Computation and Simulation",
issn = "0094-9655",
publisher = "Taylor and Francis Ltd.",
number = "1",

}

A very flexible hybrid censoring scheme and its Fisher information. / Park, Sangun; Balakrishnan, N.

In: Journal of Statistical Computation and Simulation, Vol. 82, No. 1, 01.01.2012, p. 41-50.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A very flexible hybrid censoring scheme and its Fisher information

AU - Park, Sangun

AU - Balakrishnan, N.

PY - 2012/1/1

Y1 - 2012/1/1

N2 - Various hybrid censoring schemes, which are mixtures of Type I and Type II censoring schemes, have been suggested for flexibility in termination time and efficiency level. In this paper, we propose a general hybrid censoring scheme to be a censoring scheme with Type I or Type II bounds which provides more flexible termination time and efficiency level. The Type I hybrid censoring scheme can be interpreted as a Type I censoring scheme with a Type II upper bound, while the generalized Type I hybrid censoring can be interpreted as a Type I censoring scheme with Type II lower and upper bounds. The bounds involved in the termination can also be a hybrid. We then show that the unified hybrid censoring scheme of Balakrishnan et al. [Exact likelihood inference based on an unified hybrid censored sample from the exponential distribution, J. Statist. Comput. Simul. 78 (2008), pp. 475-488] is a special case of the general hybrid censoring scheme. Finally, we discuss several new hybrid censoring schemes and evaluate the Fisher information contained in them.

AB - Various hybrid censoring schemes, which are mixtures of Type I and Type II censoring schemes, have been suggested for flexibility in termination time and efficiency level. In this paper, we propose a general hybrid censoring scheme to be a censoring scheme with Type I or Type II bounds which provides more flexible termination time and efficiency level. The Type I hybrid censoring scheme can be interpreted as a Type I censoring scheme with a Type II upper bound, while the generalized Type I hybrid censoring can be interpreted as a Type I censoring scheme with Type II lower and upper bounds. The bounds involved in the termination can also be a hybrid. We then show that the unified hybrid censoring scheme of Balakrishnan et al. [Exact likelihood inference based on an unified hybrid censored sample from the exponential distribution, J. Statist. Comput. Simul. 78 (2008), pp. 475-488] is a special case of the general hybrid censoring scheme. Finally, we discuss several new hybrid censoring schemes and evaluate the Fisher information contained in them.

UR - http://www.scopus.com/inward/record.url?scp=84862925650&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84862925650&partnerID=8YFLogxK

U2 - 10.1080/00949655.2010.521503

DO - 10.1080/00949655.2010.521503

M3 - Article

VL - 82

SP - 41

EP - 50

JO - Journal of Statistical Computation and Simulation

JF - Journal of Statistical Computation and Simulation

SN - 0094-9655

IS - 1

ER -