Consequences of Not Interpreting Structure Coefficients in Published CFA Research: A Reminder

By J. Graham, A. Guthrie, B. Thompson. 2003

191 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/fd6b3bbabeecfd53ea74d04b0f4f92d520ff9f47

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

1. Reid Bates
2. Elwood F. Holton III
3. John-Paul Hatala
4. David N. Nusbaum
5. Lisa Linnenbrink-Garcia
6. Kenneth G. Rice
7. Thomas D. Fletcher
8. J. Graham

In Statistics and Probability

1. Reid Bates
2. Elwood F. Holton III
3. John-Paul Hatala
4. Lisa Linnenbrink-Garcia
5. Kenneth G. Rice
6. Stuart J. H. Biddle
7. C. K. John Wang
8. J. Graham

Citations in the corpus

• Measuring Situational Interest in Academic Domains (2010, background): “Following the guidelines put forth by Graham et al. (2003), an examination of the structure coefficients revealed no additional concerns and confirmed the pattern coefficient results.”
• A revised learning transfer system inventory: factorial replication and validation (2012, methodology): “When factors are correlated as in the models tested in this study, it is always the case that the factors for which the pattern coefficients are constrained to zero will have structure coefficients not equal to zero (Graham, Guthrie, and Thompson 2003).”
• Development of the Competitive Work Environment Scale: A Multidimensional Climate Construct (2010, background): “Per Graham, Guthrie, and Thompson (2003) and Henson and Roberts (2006) we report both the pattern and structure coefficients.”
• The role of emotional dysregulation in perfectionism and psychological distress. (2006, background): “Structure coefficients are the correlations between measured indicators and latent variables (Graham et al., 2003).”
• Physical Self-Concept in Adolescence: Generalizability of a Multidimensional, Hierarchical Model Across Gender and Grade (2005, background): “Furthermore, in no case did the structure coefficient for each observed item exceed the value for the pattern coefficient on the factor it was set to measure, indicating that hypothesized structure was the most tenable (Graham et al., 2003).”
• The General Linear Model as Structural Equation Modeling (2008, methodology): “Discussions of computing and interpreting structure coefficients for a variety of statistical procedures are available in the literature (Courville & Thompson, 2001; Graham et al., 2003; Thompson, 1990, 1997).”