Result Details

Statistical analysis of type I multiply left-censored samples from exponential distribution

FUSEK, M.; MICHÁLEK, J. Statistical analysis of type I multiply left-censored samples from exponential distribution. JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION, 2015, vol. 85, no. 11, p. 2148-2163. ISSN: 0094-9655.

Type

journal article

Language

English

Authors

Fusek Michal, Ing., Ph.D., UMAT (FEEC)
Michálek Jaroslav, doc. RNDr., CSc., FME (FME)

Abstract

Left-censored data with one or more detection limits often arise in environmental contexts. The computational procedure for calculation of maximum likelihood estimators of the parameter for Type I multiply left-censored data from underlying exponential
distribution is suggested and used considering various numbers of detection limits. The expected Fisher information measure (FIM) is analytically determined and its performance is compared with sample (observed) FIM using simulations. Simulations are focused primarily on the properties of estimators for small sample sizes. Moreover, the simulations follow the possible applications of the results in the statistical analysis of real chemical data.

Keywords

multiply left-censored sample; maximum likelihood estimator; exponential distribution; Fisher information measure; Type I censoring

Published

2015

Pages

2148–2163

Journal

JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION, vol. 85, no. 11, ISSN 0094-9655

DOI

10.1080/00949655.2014.923886

UT WoS

000353463500002

EID Scopus

2-s2.0-84928634866

BibTeX

@article{BUT107489,
  author="Michal {Fusek} and Jaroslav {Michálek}",
  title="Statistical analysis of type I multiply left-censored samples from exponential distribution",
  journal="JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION",
  year="2015",
  volume="85",
  number="11",
  pages="2148--2163",
  doi="10.1080/00949655.2014.923886",
  issn="0094-9655"
}

Departments

Department of Mathematics (UMAT)
Dept. of Statistics and Optimization (IM DSO)