The generalised bootstrap for clustered data

Zhen Pang; A. H. Welsh

doi:10.1504/IJDATS.2014.066604

The generalised bootstrap for clustered data

Zhen Pang, A. H. Welsh^*

^*Corresponding author for this work

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

3 Citations (Scopus)

Abstract

We extend the generalised bootstrap of Chatterjee and Bose (2005) to bootstrap clustered data. We show by simulations and theoretical arguments that the variance of the random weights used in the generalised bootstrap is critical in determining the performance of the bootstrap when we use the distribution of the bootstrap estimate to approximate the sampling distribution of the parameter. In particular, we show that for consistency, the weights should be chosen to have variance one.

Original language	English
Pages (from-to)	407-415
Number of pages	9
Journal	International Journal of Data Analysis Techniques and Strategies
Volume	6
Issue number	4
DOIs	https://doi.org/10.1504/IJDATS.2014.066604
Publication status	Published - 1 Jan 2014

Access to Document

10.1504/IJDATS.2014.066604

Cite this

@article{adc934aa40854cffa8420e8c5811d63b,

title = "The generalised bootstrap for clustered data",

abstract = "We extend the generalised bootstrap of Chatterjee and Bose (2005) to bootstrap clustered data. We show by simulations and theoretical arguments that the variance of the random weights used in the generalised bootstrap is critical in determining the performance of the bootstrap when we use the distribution of the bootstrap estimate to approximate the sampling distribution of the parameter. In particular, we show that for consistency, the weights should be chosen to have variance one.",

keywords = "Bootstrap, Clustered data, Generalised bootstrap, Quasi-likelihood estimation, Unbalanced data, Variance components",

author = "Zhen Pang and Welsh, {A. H.}",

note = "Publisher Copyright: Copyright {\textcopyright} 2014 Inderscience Enterprises Ltd.",

year = "2014",

month = jan,

day = "1",

doi = "10.1504/IJDATS.2014.066604",

language = "English",

volume = "6",

pages = "407--415",

journal = "International Journal of Data Analysis Techniques and Strategies",

issn = "1755-8050",

publisher = "Inderscience",

number = "4",

}

TY - JOUR

T1 - The generalised bootstrap for clustered data

AU - Pang, Zhen

AU - Welsh, A. H.

PY - 2014/1/1

Y1 - 2014/1/1

N2 - We extend the generalised bootstrap of Chatterjee and Bose (2005) to bootstrap clustered data. We show by simulations and theoretical arguments that the variance of the random weights used in the generalised bootstrap is critical in determining the performance of the bootstrap when we use the distribution of the bootstrap estimate to approximate the sampling distribution of the parameter. In particular, we show that for consistency, the weights should be chosen to have variance one.

AB - We extend the generalised bootstrap of Chatterjee and Bose (2005) to bootstrap clustered data. We show by simulations and theoretical arguments that the variance of the random weights used in the generalised bootstrap is critical in determining the performance of the bootstrap when we use the distribution of the bootstrap estimate to approximate the sampling distribution of the parameter. In particular, we show that for consistency, the weights should be chosen to have variance one.

KW - Bootstrap

KW - Clustered data

KW - Generalised bootstrap

KW - Quasi-likelihood estimation

KW - Unbalanced data

KW - Variance components

UR - http://www.scopus.com/inward/record.url?scp=84920163730&partnerID=8YFLogxK

U2 - 10.1504/IJDATS.2014.066604

DO - 10.1504/IJDATS.2014.066604

M3 - Article

SN - 1755-8050

VL - 6

SP - 407

EP - 415

JO - International Journal of Data Analysis Techniques and Strategies

JF - International Journal of Data Analysis Techniques and Strategies

IS - 4

ER -

The generalised bootstrap for clustered data

Abstract

Access to Document

Other files and links

Fingerprint

Cite this