New bootstrap confidence intervals for means of positively skewed distributions

Santu Ghosh, Alan M. Polansky

Research output: Contribution to journalArticle

Abstract

In this paper, we consider the problem of constructing non parametric confidence intervals for the mean of a positively skewed distribution. We suggest calibrated, smoothed bootstrap upper and lower percentile confidence intervals. For the theoretical properties, we show that the proposed one-sided confidence intervals have coverage probability α + O(n− 3/2). This is an improvement upon the traditional bootstrap confidence intervals in terms of coverage probability. A version smoothed approach is also considered for constructing a two-sided confidence interval and its theoretical properties are also studied. A simulation study is performed to illustrate the performance of our confidence interval methods. We then apply the methods to a real data set.

Original languageEnglish (US)
Pages (from-to)6915-6927
Number of pages13
JournalCommunications in Statistics - Theory and Methods
Volume45
Issue number23
DOIs
StatePublished - Dec 1 2016

Fingerprint

Bootstrap Confidence Intervals
Skewed Distribution
Confidence interval
Coverage Probability
Smoothed Bootstrap
Interval Probability
Interval Methods
Percentile
Simulation Study

Keywords

  • Bandwidth parameter
  • Bootstrap percentile method
  • Bootstrap percentile-t method
  • Confidence interval

ASJC Scopus subject areas

  • Statistics and Probability

Cite this

New bootstrap confidence intervals for means of positively skewed distributions. / Ghosh, Santu; Polansky, Alan M.

In: Communications in Statistics - Theory and Methods, Vol. 45, No. 23, 01.12.2016, p. 6915-6927.

Research output: Contribution to journalArticle

@article{1e31106547f64a88ac7665900f057c9b,
title = "New bootstrap confidence intervals for means of positively skewed distributions",
abstract = "In this paper, we consider the problem of constructing non parametric confidence intervals for the mean of a positively skewed distribution. We suggest calibrated, smoothed bootstrap upper and lower percentile confidence intervals. For the theoretical properties, we show that the proposed one-sided confidence intervals have coverage probability α + O(n− 3/2). This is an improvement upon the traditional bootstrap confidence intervals in terms of coverage probability. A version smoothed approach is also considered for constructing a two-sided confidence interval and its theoretical properties are also studied. A simulation study is performed to illustrate the performance of our confidence interval methods. We then apply the methods to a real data set.",
keywords = "Bandwidth parameter, Bootstrap percentile method, Bootstrap percentile-t method, Confidence interval",
author = "Santu Ghosh and Polansky, {Alan M.}",
year = "2016",
month = "12",
day = "1",
doi = "10.1080/03610926.2014.972569",
language = "English (US)",
volume = "45",
pages = "6915--6927",
journal = "Communications in Statistics - Theory and Methods",
issn = "0361-0926",
publisher = "Taylor and Francis Ltd.",
number = "23",

}

TY - JOUR

T1 - New bootstrap confidence intervals for means of positively skewed distributions

AU - Ghosh, Santu

AU - Polansky, Alan M.

PY - 2016/12/1

Y1 - 2016/12/1

N2 - In this paper, we consider the problem of constructing non parametric confidence intervals for the mean of a positively skewed distribution. We suggest calibrated, smoothed bootstrap upper and lower percentile confidence intervals. For the theoretical properties, we show that the proposed one-sided confidence intervals have coverage probability α + O(n− 3/2). This is an improvement upon the traditional bootstrap confidence intervals in terms of coverage probability. A version smoothed approach is also considered for constructing a two-sided confidence interval and its theoretical properties are also studied. A simulation study is performed to illustrate the performance of our confidence interval methods. We then apply the methods to a real data set.

AB - In this paper, we consider the problem of constructing non parametric confidence intervals for the mean of a positively skewed distribution. We suggest calibrated, smoothed bootstrap upper and lower percentile confidence intervals. For the theoretical properties, we show that the proposed one-sided confidence intervals have coverage probability α + O(n− 3/2). This is an improvement upon the traditional bootstrap confidence intervals in terms of coverage probability. A version smoothed approach is also considered for constructing a two-sided confidence interval and its theoretical properties are also studied. A simulation study is performed to illustrate the performance of our confidence interval methods. We then apply the methods to a real data set.

KW - Bandwidth parameter

KW - Bootstrap percentile method

KW - Bootstrap percentile-t method

KW - Confidence interval

UR - http://www.scopus.com/inward/record.url?scp=84984982142&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84984982142&partnerID=8YFLogxK

U2 - 10.1080/03610926.2014.972569

DO - 10.1080/03610926.2014.972569

M3 - Article

VL - 45

SP - 6915

EP - 6927

JO - Communications in Statistics - Theory and Methods

JF - Communications in Statistics - Theory and Methods

SN - 0361-0926

IS - 23

ER -