Alternatives to difference scores: Polynomial regression analysis and response surface methodology.

By J. Edwards. 2002

693 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/2e9ee65cb88df1d4d658c506fd8ca3c01702e1ed

How researchers see this paper

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

Citations in the corpus

The Psychology of Rivalry: A Relationally Dependent Analysis of Competition (2010, background): “A number of methodological concerns have been raised in regard to using difference scores as predictor variables, most notably, the fact that they may confound the effects of their component measures (Edwards, 2002; Edwards & Parry, 1993)—in this case, the individual attributes of each team.”
When Does (Mis)Fit in Customer Orientation Matter for Frontline Employees’ Job Satisfaction and Performance? (2016, background): “…(mis)fit (e.g., Siguaw et al. 1994); however, this approach has been widely criticized for the conceptual and methodological problems it creates in the areas of reliability, discriminant validity, spurious correlation, and variance restriction (Edwards 2002; Peter, Churchill, and Brown 1993).”
Testing Fit Patterns with Polynomial Regression Models (2015, methodology): “A practical solution for an easier interpretation is to plot the regression result as a response surface (e.g., Edwards, 2002; Myers, Montgomery, & Fitzgerald, 2009).”
Does Seeing “Eye To Eye” Affect Work Engagement and Organizational Citizenship Behavior? A Role Theory Perspective on LMX Agreement (2014, methodology): “…surface (that is, the first principal axis) is located along the congruence line, and thus has a slope (p11) of 1 and an intercept (p10) of 0 (Edwards, 2002; Edwards & 4 We assessed age similarity as an absolute difference score to save degrees of freedomandbecause age similarity wasnot a…”
Erratum to: Polynomial Regression with Response Surface Analysis: A Powerful Approach for Examining Moderation and Overcoming Limitations of Difference Scores (2010, background): “Rather than examining the regression coefficients as would be done in a common regression analysis, if the R2 (variance in the outcome variable explained by the regression equation) is significantly different from zero (Edwards 2002), the results of the polynomial regression are evaluated with regar”
Leader–member exchange (LMX) differentiation and work outcomes: conceptual clarification and critical review (2018, background): “…examine both the degree (i.e., magnitude) and the direction (i.e., low relative status vs. high relative status) of LMX relative position as well as the absolute levels of the components of LMX relative position (i.e., individual LMX quality and team mean LMX quality; see Edwards, 2002).”
Employee and Coworker Idiosyncratic Deals: Implications for Emotional Exhaustion and Deviant Behaviors (2018, methodology): “We combined the techniques of Actor-Partner Interdependence Model (APIM) (Cook & Kenny, 2005; Kenny, Kashy, & Cook, 2006) and polynomial regression (Edwards, 2002) in testing our hypotheses.”
Mutuality in leader–subordinate empowerment expectation: Its impact on role ambiguity and intrinsic motivation ☆ (2013, methodology): “The polynomial regression analysis begins with a representation of the conceptual model as unconstrained regression equations (Edwards, 2002; Edwards & Parry, 1993).”
A Multicultural Test of the Theory of Work Adjustment: Investigating the Role of Heterosexism and Fit Perceptions in the Job Satisfaction of Lesbian, Gay, and Bisexual Employees. (2005, methodology): “As indicated in reviews of measurement of P-E fit, all methods of measurement possess drawbacks (Edwards, 1991; Edwards, 2002; Kristof, 1996).”
Individual ambidexterity: the duality of exploration and exploitation and its relationship with innovative performance (2017, background): “Particularly difference scores, which are calculated by subtracting measurement scores of exploration and exploitation, have been criticized due to problems such as decreased reliability and confounding of effects (Edwards, 1994, 2002; Edwards & Parry, 1993).”