2021
DOI: 10.1037/cbs0000267
|View full text |Cite
|
Sign up to set email alerts
|

Incidence and interpretation of statistical suppression in psychological research.

Abstract: Suppressors are third variables that increase the predictive power of one or more predictors by suppressing their irrelevant variance when included in a regression model. Although theoretically and statistically useful, no research has addressed the frequency or interpretation of statistical suppression (SS) in the psychological literature. Two studies explored the nature and interpretation of SS. In the first study, regression analyses were reviewed to determine the frequency with which SS occurs in psycholog… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
8
0
1

Year Published

2022
2022
2024
2024

Publication Types

Select...
7
1

Relationship

0
8

Authors

Journals

citations
Cited by 25 publications
(9 citation statements)
references
References 33 publications
0
8
0
1
Order By: Relevance
“…A suppressor variable is one which increases the predictive validity of another variable by its inclusion in the regression equation (Conger, 1974), whereby predictive validity refers to the magnitude of the regression coefficient. Thus, in case of suppression, the magnitude of the relationship between the independent and dependent variable increases when the suppressor variable is added to the regression equation (MacKinnon et al, 2000;Martinez Gutierrez & Cribbie, 2021). In our study, we expected qualitative challenge and hindrance demands to act as suppressor variables regarding the relationship between time pressure and work engagement as well as time pressure and self-esteem.…”
Section: Suppressor Variablesmentioning
confidence: 81%
“…A suppressor variable is one which increases the predictive validity of another variable by its inclusion in the regression equation (Conger, 1974), whereby predictive validity refers to the magnitude of the regression coefficient. Thus, in case of suppression, the magnitude of the relationship between the independent and dependent variable increases when the suppressor variable is added to the regression equation (MacKinnon et al, 2000;Martinez Gutierrez & Cribbie, 2021). In our study, we expected qualitative challenge and hindrance demands to act as suppressor variables regarding the relationship between time pressure and work engagement as well as time pressure and self-esteem.…”
Section: Suppressor Variablesmentioning
confidence: 81%
“…Social support was positively associated with somatic symptoms in the multivariate model, despite being associated with fewer somatic symptoms in the bivariate analysis (Supplemental File 2 ). This was due to negative suppression, which happens when controlling for a third variable reverses the sign of another predictor variable [ 66 ]. In this case, only when self-esteem was in the regression did social support have a positive coefficient rather than the expected negative coefficient.…”
Section: Resultsmentioning
confidence: 99%
“…Wurm and Fisicaro (2014) concluded from a study on multicollinearity in psycholinguistic research, "[…] suppression does not indicate computational problems or model instability" (p. 47). The debate on suppression effects could be important because a recent literature review showed that one-third of the publications in psychology journals contain evidence of statistical suppression effects (Martinez Gutierrez & Cribbie, 2021).…”
Section: Discussionmentioning
confidence: 99%