Construction of the average variance extracted index for construct validation in structural equation models with adaptive regressions

A range of indicators, such as the average variance extracted (AVE), is commonly used to validate constructs. In statistics, AVE is a measure of the amount of variance that is captured by a construct in relation to the amount of variance due to measurement error. These conventional indices are forme...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Communications in statistics. Simulation and computation Jg. 52; H. 4; S. 1639 - 1650
Hauptverfasser: dos Santos, Patricia Mendes, Cirillo, Marcelo Ângelo
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Philadelphia Taylor & Francis 03.04.2023
Taylor & Francis Ltd
Schlagworte:
Adaptive regression
Error analysis
Kurtosis
Monte Carlo simulation
Multivariate statistical analysis
Outliers
Outliers (statistics)
Structural equation model
Structural equation modeling
Structural models
Variance
ISSN:0361-0918, 1532-4141
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:A range of indicators, such as the average variance extracted (AVE), is commonly used to validate constructs. In statistics, AVE is a measure of the amount of variance that is captured by a construct in relation to the amount of variance due to measurement error. These conventional indices are formed by factor loadings resulting from estimated least squares or maximum likelihood regressions. Thus, a new proposition that provides new factor loadings may result in a more informative AVE index. Consequently, this study consists of the improvement of the index by using adaptive regressions. A Monte Carlo simulation study was performed considering different numbers of outliers generated by distributions with symmetry deviations and excess kurtosis and sample sizes defined as n = 50, 100, and 200. The conclusion was that, in formative structural models, the adaptive linear regression (ALR) method showed good efficiency for correctly specified models. The results obtained from the ALR method for models with specification errors showed low efficiency, as expected.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0361-0918
1532-4141
DOI:10.1080/03610918.2021.1888122