Use of Structure Coefficients in Published Multiple Regression Articles: β is not Enough

By T. Courville, B. Thompson. 2001

484 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/0920b70ad01a4788223887849c839eaddc6cd1c8

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

In Statistics and Probability

Citations in the corpus

Factors Affecting Relative Weights: The Influence of Sampling and Measurement Error (2004, background): “A measure of relative importance is useful when one is attempting to explain or describe the relationships between predictors and a criterion, as opposed to when multiple regression is used simply to identify the most predictive model (Courville & Thompson, 2001).”
Relations between characteristics of workplace practices and types of informal work‐related learning: A survey study among Dutch Police (2008, methodology): “The standardized regression weights ( b’s) and R2 values were supplemented by structure coefficients (rs ) that are not suppressed or inflated by collinearity (Courville & Thompson, 2001).”
Variability and Prediction of Measurement Error in Kolb’s Learning Style Inventory Scores a Reliability Generalization Study (2002, background): “Furthermore, examination of the beta weights and structure coefficients (Courville & Thompson, 2001) revealed that the test form primarily contributed to these effects, particularly in the internal consistency case.”
Reporting Practice and Use of Exploratory Factor Analysis in Educational Research Journals: Errors and Explanation (2001, background): “(cf. Courville & Thompson, 2001; Henson, 2002), examination of only the pattern coefficients”
The Convergent, Discriminant, and Incremental Validity of Scores on a Self-Report Measure of Cultural Intelligence (2009, background): “The structure coefficients are also included in Table 4 (Courville & Thompson, 2001).”
Tools to Support Interpreting Multiple Regression in the Face of Multicollinearity (2012, methodology): “Unfortunately, many researchers rely heavily on standardized (beta, β) or unstandardized (slope) regression weights when interpreting MR results (Courville and Thompson, 2001; Zientek and Thompson, 2009).”
Conducting and Interpreting Canonical Correlation Analysis in Personality Research: A User-Friendly Primer (2005, methodology): “We present an entire example of a CCA analysis using SPSS (Version 11.0) with personality assessment data.”
Examining Teacher–Child Relationships and Achievement as Part of an Ecological Model of Development (2007, background): “Only by examining both the structure coefficients and β weights is it possible to determine if a variable contributes directly or indirectly to predicting the outcome (Courville & Thompson, 2001).”
Gratitude for small and large favors: A behavioral test (2007, background): “In contrast, structure coefficients (ie, bivariate r yx / R ; see Courville & Thompson, 2001 ) revealed that both the Favor manipulation ( r s = 0.”
A Communication Researchers' Guide to Null Hypothesis Significance Testing and Alternatives. (2008, background): “…significance testing of b can be misleading because b can be near zero even when the predictor explains a substantial amount of the variance in the outcome variable when other predictors correlated with the predictor claim the shared variance (Courville & Thompson, 2001; Thompson & Borrello, 1985).”
Socio‐economic background, parental involvement and teacher perceptions of these in relation to pupil achievement (2007, background): “The standardized regression coefficients are presented in Table 5, together with the structure coefficients (rs) which are not suppressed or inflated by colinearity (Thompson & Borello, 1985; Courville & Thompson, 2001).”