Assessing and comparing the accuracy of various bootstrap methods

Yaqian Zhu; John Kolassa

doi:10.1080/03610918.2017.1348516

Assessing and comparing the accuracy of various bootstrap methods

Yaqian Zhu, John Kolassa

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

Abstract

We evaluate the performance of various bootstrap methods for constructing confidence intervals for mean and median of several common distributions. Using Monte Carlo simulation, we assessed performance by looking at coverage percentages and average confidence interval lengths. Poor performance is characterized by coverage deviating from 0.95 and large confidence interval lengths. Undercoverage is of greater concern than overcoverage. We also assess the performance of bootstrap methods in estimating the parameters of the Cox Proportional Hazard model and Accelerated Failure Time model.

Original language	English (US)
Pages (from-to)	2436-2453
Number of pages	18
Journal	Communications in Statistics: Simulation and Computation
Volume	47
Issue number	8
DOIs	https://doi.org/10.1080/03610918.2017.1348516
State	Published - Sep 14 2018

All Science Journal Classification (ASJC) codes

Statistics and Probability
Modeling and Simulation

Keywords

Accelerated failure time model
Bootstrap
Cox regression model

Access to Document

10.1080/03610918.2017.1348516

Cite this

@article{5bf5b670e39744eba891c4637009e4b5,

title = "Assessing and comparing the accuracy of various bootstrap methods",

abstract = "We evaluate the performance of various bootstrap methods for constructing confidence intervals for mean and median of several common distributions. Using Monte Carlo simulation, we assessed performance by looking at coverage percentages and average confidence interval lengths. Poor performance is characterized by coverage deviating from 0.95 and large confidence interval lengths. Undercoverage is of greater concern than overcoverage. We also assess the performance of bootstrap methods in estimating the parameters of the Cox Proportional Hazard model and Accelerated Failure Time model.",

keywords = "Accelerated failure time model, Bootstrap, Cox regression model",

author = "Yaqian Zhu and John Kolassa",

note = "Funding Information: This work was funded by the National Science Foundation grant CCF-1559855. Publisher Copyright: {\textcopyright} 2018, {\textcopyright} 2018 Taylor & Francis Group, LLC.",

year = "2018",

month = sep,

day = "14",

doi = "10.1080/03610918.2017.1348516",

language = "English (US)",

volume = "47",

pages = "2436--2453",

journal = "Communications in Statistics: Simulation and Computation",

issn = "0361-0918",

publisher = "Taylor and Francis Ltd.",

number = "8",

}

TY - JOUR

T1 - Assessing and comparing the accuracy of various bootstrap methods

AU - Zhu, Yaqian

AU - Kolassa, John

PY - 2018/9/14

Y1 - 2018/9/14

N2 - We evaluate the performance of various bootstrap methods for constructing confidence intervals for mean and median of several common distributions. Using Monte Carlo simulation, we assessed performance by looking at coverage percentages and average confidence interval lengths. Poor performance is characterized by coverage deviating from 0.95 and large confidence interval lengths. Undercoverage is of greater concern than overcoverage. We also assess the performance of bootstrap methods in estimating the parameters of the Cox Proportional Hazard model and Accelerated Failure Time model.

AB - We evaluate the performance of various bootstrap methods for constructing confidence intervals for mean and median of several common distributions. Using Monte Carlo simulation, we assessed performance by looking at coverage percentages and average confidence interval lengths. Poor performance is characterized by coverage deviating from 0.95 and large confidence interval lengths. Undercoverage is of greater concern than overcoverage. We also assess the performance of bootstrap methods in estimating the parameters of the Cox Proportional Hazard model and Accelerated Failure Time model.

KW - Accelerated failure time model

KW - Bootstrap

KW - Cox regression model

UR - http://www.scopus.com/inward/record.url?scp=85026497928&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85026497928&partnerID=8YFLogxK

U2 - 10.1080/03610918.2017.1348516

DO - 10.1080/03610918.2017.1348516

M3 - Article

AN - SCOPUS:85026497928

SN - 0361-0918

VL - 47

SP - 2436

EP - 2453

JO - Communications in Statistics: Simulation and Computation

JF - Communications in Statistics: Simulation and Computation

IS - 8

ER -

Assessing and comparing the accuracy of various bootstrap methods

Abstract

All Science Journal Classification (ASJC) codes

Keywords

Access to Document

Other files and links

Fingerprint

Cite this