Abstract
The purpose of this study is to propose a way to express and implement paired comparison analysis in a framework of structural equation modeling (SEM). By this method, one can perform paired comparison using widely available SEM programs and can develop a variety of models for specific purposes. Here, three models are shown. One is a model for performing basic paired comparison by using SEM. Another is an expanded model which makes it possible to apply analysis of variance (ANOVA) or regression analysis to the result of paired comparison. A third model is for paired comparison of latent factors. All models are illustrated with actual numerical examples.
Original language | English |
---|---|
Pages (from-to) | 299-307 |
Number of pages | 9 |
Journal | Shinrigaku Kenkyu |
Volume | 75 |
Issue number | 4 |
Publication status | Published - 2004 Oct |
Fingerprint
Keywords
- Covariance structure
- Paired comparison
- Structural equation modeling
ASJC Scopus subject areas
- Psychology(all)
Cite this
Paired comparison analysis by using structural equation modeling : Scheffe's method and its improvements. / Toyoda, Hideki; Ozaki, Kouken; Murohashi, Hiroto; Haga, Mayomi.
In: Shinrigaku Kenkyu, Vol. 75, No. 4, 10.2004, p. 299-307.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Paired comparison analysis by using structural equation modeling
T2 - Scheffe's method and its improvements
AU - Toyoda, Hideki
AU - Ozaki, Kouken
AU - Murohashi, Hiroto
AU - Haga, Mayomi
PY - 2004/10
Y1 - 2004/10
N2 - The purpose of this study is to propose a way to express and implement paired comparison analysis in a framework of structural equation modeling (SEM). By this method, one can perform paired comparison using widely available SEM programs and can develop a variety of models for specific purposes. Here, three models are shown. One is a model for performing basic paired comparison by using SEM. Another is an expanded model which makes it possible to apply analysis of variance (ANOVA) or regression analysis to the result of paired comparison. A third model is for paired comparison of latent factors. All models are illustrated with actual numerical examples.
AB - The purpose of this study is to propose a way to express and implement paired comparison analysis in a framework of structural equation modeling (SEM). By this method, one can perform paired comparison using widely available SEM programs and can develop a variety of models for specific purposes. Here, three models are shown. One is a model for performing basic paired comparison by using SEM. Another is an expanded model which makes it possible to apply analysis of variance (ANOVA) or regression analysis to the result of paired comparison. A third model is for paired comparison of latent factors. All models are illustrated with actual numerical examples.
KW - Covariance structure
KW - Paired comparison
KW - Structural equation modeling
UR - http://www.scopus.com/inward/record.url?scp=15744393186&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=15744393186&partnerID=8YFLogxK
M3 - Article
C2 - 15747549
AN - SCOPUS:15744393186
VL - 75
SP - 299
EP - 307
JO - Shinrigaku Kenkyu
JF - Shinrigaku Kenkyu
SN - 0021-5236
IS - 4
ER -