Model specification search using a genetic algorithm with factor reordering for a simple structure factor analysis model

Hiroto Murohashi, Hideki Toyoda

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Many techniques for automated model specification search based on numerical indices have been proposed, but no single decisive method has yet been determined. In the present article, the performance and features of the model specification search method using a genetic algorithm (GA) were verified. A GA is a robust and simple metaheuristic algorithm with great searching power. While there has already been some research applying metaheuristics to the model fitting task, we focus here on the search for a simple structure factor analysis model and propose a customized algorithm for dealing with certain problems specific to that situation. First, implementation of model specification search using a GA with factor reordering for a simple structure factor analysis is proposed. Then, through a simulation study using generated data with a known true structure and through example analysis using real data, the effectiveness and applicability of the proposed method were demonstrated.

Original languageEnglish
Pages (from-to)179-191
Number of pages13
JournalJapanese Psychological Research
Volume49
Issue number3
DOIs
Publication statusPublished - 2007 Sep

Fingerprint

Statistical Factor Analysis
Research

Keywords

  • Combinational optimization problem
  • Factor analysis
  • Genetic algorithm
  • Model specification search
  • Structural equation modeling

ASJC Scopus subject areas

  • Psychology(all)

Cite this

Model specification search using a genetic algorithm with factor reordering for a simple structure factor analysis model. / Murohashi, Hiroto; Toyoda, Hideki.

In: Japanese Psychological Research, Vol. 49, No. 3, 09.2007, p. 179-191.

Research output: Contribution to journalArticle

@article{d1010e74cee2447486c57c6ecbc9cf72,
title = "Model specification search using a genetic algorithm with factor reordering for a simple structure factor analysis model",
abstract = "Many techniques for automated model specification search based on numerical indices have been proposed, but no single decisive method has yet been determined. In the present article, the performance and features of the model specification search method using a genetic algorithm (GA) were verified. A GA is a robust and simple metaheuristic algorithm with great searching power. While there has already been some research applying metaheuristics to the model fitting task, we focus here on the search for a simple structure factor analysis model and propose a customized algorithm for dealing with certain problems specific to that situation. First, implementation of model specification search using a GA with factor reordering for a simple structure factor analysis is proposed. Then, through a simulation study using generated data with a known true structure and through example analysis using real data, the effectiveness and applicability of the proposed method were demonstrated.",
keywords = "Combinational optimization problem, Factor analysis, Genetic algorithm, Model specification search, Structural equation modeling",
author = "Hiroto Murohashi and Hideki Toyoda",
year = "2007",
month = "9",
doi = "10.1111/j.1468-5884.2007.00345.x",
language = "English",
volume = "49",
pages = "179--191",
journal = "Japanese Psychological Research",
issn = "0021-5368",
publisher = "Wiley-Blackwell",
number = "3",

}

TY - JOUR

T1 - Model specification search using a genetic algorithm with factor reordering for a simple structure factor analysis model

AU - Murohashi, Hiroto

AU - Toyoda, Hideki

PY - 2007/9

Y1 - 2007/9

N2 - Many techniques for automated model specification search based on numerical indices have been proposed, but no single decisive method has yet been determined. In the present article, the performance and features of the model specification search method using a genetic algorithm (GA) were verified. A GA is a robust and simple metaheuristic algorithm with great searching power. While there has already been some research applying metaheuristics to the model fitting task, we focus here on the search for a simple structure factor analysis model and propose a customized algorithm for dealing with certain problems specific to that situation. First, implementation of model specification search using a GA with factor reordering for a simple structure factor analysis is proposed. Then, through a simulation study using generated data with a known true structure and through example analysis using real data, the effectiveness and applicability of the proposed method were demonstrated.

AB - Many techniques for automated model specification search based on numerical indices have been proposed, but no single decisive method has yet been determined. In the present article, the performance and features of the model specification search method using a genetic algorithm (GA) were verified. A GA is a robust and simple metaheuristic algorithm with great searching power. While there has already been some research applying metaheuristics to the model fitting task, we focus here on the search for a simple structure factor analysis model and propose a customized algorithm for dealing with certain problems specific to that situation. First, implementation of model specification search using a GA with factor reordering for a simple structure factor analysis is proposed. Then, through a simulation study using generated data with a known true structure and through example analysis using real data, the effectiveness and applicability of the proposed method were demonstrated.

KW - Combinational optimization problem

KW - Factor analysis

KW - Genetic algorithm

KW - Model specification search

KW - Structural equation modeling

UR - http://www.scopus.com/inward/record.url?scp=34548755038&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34548755038&partnerID=8YFLogxK

U2 - 10.1111/j.1468-5884.2007.00345.x

DO - 10.1111/j.1468-5884.2007.00345.x

M3 - Article

AN - SCOPUS:34548755038

VL - 49

SP - 179

EP - 191

JO - Japanese Psychological Research

JF - Japanese Psychological Research

SN - 0021-5368

IS - 3

ER -