The table 2 fallacy: presenting and interpreting confounder and modifier coefficients.

By D. Westreich, Sander Greenland. American Journal of Epidemiology, 2013

1,042 citations recorded by the source corpus.

How researchers see this paper

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

A Complete Generalized Adjustment Criterion (2015, background): “A few small graphs also suffice to refute the “Table 2 fallacy” (Westreich and Greenland, 2013), which is the belief that the coefficients in multiple regression models are “mutually adjusted”.”
On the Nuisance of Control Variables in Regression Analysis (2020, background): “This is because even valid controls are often correlated with other unobserved factors, which render their marginal effects uninterpretable from a causal inference perspective (Westreich and Greenland, 2013; Keele et al., 2020).”
Developing clinical prediction models: a step-by-step guide (2024, positive): “Regardless of the method we choose to assess predictor importance, we should be careful in our interpretations; associations seen in data might not reflect causal relationships (eg, see the “Table 2 fallacy” 111 ).”
Use of directed acyclic graphs (DAGs) to identify confounders in applied health research: review and recommendations (2020, background): “This is exemplified by the ‘Table 2 fallacy’, which occurs when the coefficients for two or more ‘risk factors’ in a multivariable regression model are (mistakenly) interpreted as estimates for meaningful causal effects.(8) Causal inference approaches, such as the potential outcomes framework, promo”