The implementation of double bootstrap method in structural equation modeling

Research output: Contribution to journalArticle

Abstract

Accuracy and reliability are fiery issues in Structural Equation Modeling (SEM). The single bootstrap method was outstanding, but the double bootstrap method was overlooked. The aim of this paper is to propose the usage of double raw data bootstrap method in SEM (double BOOT SEM). Double BOOT SEM is an enhanced version of raw data bootstrap method in SEM (BOOT SEM), where we resample raw data with replacement from each of the bootstrap samples repeatedly for a number of times. The performance of double BOOT SEM, BOOT SEM and SEM are evaluated through several summary statistics and confidence intervals. Results indicate that the performance of double BOOT SEM is more efficient compared to BOOT SEM and SEM in terms of smaller summary statistics values and narrowed bootstrap intervals.

Original languageEnglish
Pages (from-to)246-255
Number of pages10
JournalASM Science Journal
Volume12
Issue numberSpecial Issue 1
Publication statusPublished - 1 Jan 2019

Fingerprint

Statistics
Scanning electron microscopy

Keywords

  • Accuracy
  • Confidence intervals
  • Double bootstrap
  • Structural equation modeling

ASJC Scopus subject areas

  • General

Cite this

The implementation of double bootstrap method in structural equation modeling. / Razak, Nor Iza Anuar; Zamzuri, Zamira Hasanah; Mohd. Suradi, Nur Riza.

In: ASM Science Journal, Vol. 12, No. Special Issue 1, 01.01.2019, p. 246-255.

Research output: Contribution to journalArticle

@article{f63faedf4fac462ba19c429ee0821f28,
title = "The implementation of double bootstrap method in structural equation modeling",
abstract = "Accuracy and reliability are fiery issues in Structural Equation Modeling (SEM). The single bootstrap method was outstanding, but the double bootstrap method was overlooked. The aim of this paper is to propose the usage of double raw data bootstrap method in SEM (double BOOT SEM). Double BOOT SEM is an enhanced version of raw data bootstrap method in SEM (BOOT SEM), where we resample raw data with replacement from each of the bootstrap samples repeatedly for a number of times. The performance of double BOOT SEM, BOOT SEM and SEM are evaluated through several summary statistics and confidence intervals. Results indicate that the performance of double BOOT SEM is more efficient compared to BOOT SEM and SEM in terms of smaller summary statistics values and narrowed bootstrap intervals.",
keywords = "Accuracy, Confidence intervals, Double bootstrap, Structural equation modeling",
author = "Razak, {Nor Iza Anuar} and Zamzuri, {Zamira Hasanah} and {Mohd. Suradi}, {Nur Riza}",
year = "2019",
month = "1",
day = "1",
language = "English",
volume = "12",
pages = "246--255",
journal = "ASM Science Journal",
issn = "1823-6782",
publisher = "Akademi Sains Malaysia",
number = "Special Issue 1",

}

TY - JOUR

T1 - The implementation of double bootstrap method in structural equation modeling

AU - Razak, Nor Iza Anuar

AU - Zamzuri, Zamira Hasanah

AU - Mohd. Suradi, Nur Riza

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Accuracy and reliability are fiery issues in Structural Equation Modeling (SEM). The single bootstrap method was outstanding, but the double bootstrap method was overlooked. The aim of this paper is to propose the usage of double raw data bootstrap method in SEM (double BOOT SEM). Double BOOT SEM is an enhanced version of raw data bootstrap method in SEM (BOOT SEM), where we resample raw data with replacement from each of the bootstrap samples repeatedly for a number of times. The performance of double BOOT SEM, BOOT SEM and SEM are evaluated through several summary statistics and confidence intervals. Results indicate that the performance of double BOOT SEM is more efficient compared to BOOT SEM and SEM in terms of smaller summary statistics values and narrowed bootstrap intervals.

AB - Accuracy and reliability are fiery issues in Structural Equation Modeling (SEM). The single bootstrap method was outstanding, but the double bootstrap method was overlooked. The aim of this paper is to propose the usage of double raw data bootstrap method in SEM (double BOOT SEM). Double BOOT SEM is an enhanced version of raw data bootstrap method in SEM (BOOT SEM), where we resample raw data with replacement from each of the bootstrap samples repeatedly for a number of times. The performance of double BOOT SEM, BOOT SEM and SEM are evaluated through several summary statistics and confidence intervals. Results indicate that the performance of double BOOT SEM is more efficient compared to BOOT SEM and SEM in terms of smaller summary statistics values and narrowed bootstrap intervals.

KW - Accuracy

KW - Confidence intervals

KW - Double bootstrap

KW - Structural equation modeling

UR - http://www.scopus.com/inward/record.url?scp=85071484759&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85071484759&partnerID=8YFLogxK

M3 - Article

VL - 12

SP - 246

EP - 255

JO - ASM Science Journal

JF - ASM Science Journal

SN - 1823-6782

IS - Special Issue 1

ER -