Overadjustment Bias and Unnecessary Adjustment in Epidemiologic Studies

TLDR

Overadjustment is inconsistently defined and refers to controlling for a variable that either increases bias or reduces precision without affecting bias. The authors define overadjustment bias as adjusting for an intermediate variable on the causal path from exposure to outcome, and unnecessary adjustment as adjusting for a variable that does not affect bias but may affect precision. They illustrate these concepts with causal diagrams and an empirical example of maternal smoking and neonatal mortality, distinguishing overadjustment bias from unnecessary adjustment. Simulations show that overadjustment bias differs from confounding or selection bias, is not a finite‑sample bias, whereas inefficiencies from unnecessary variables depend on sample size.

Abstract

Overadjustment is defined inconsistently. This term is meant to describe control (eg, by regression adjustment, stratification, or restriction) for a variable that either increases net bias or decreases precision without affecting bias. We define overadjustment bias as control for an intermediate variable (or a descending proxy for an intermediate variable) on a causal path from exposure to outcome. We define unnecessary adjustment as control for a variable that does not affect bias of the causal relation between exposure and outcome but may affect its precision. We use causal diagrams and an empirical example (the effect of maternal smoking on neonatal mortality) to illustrate and clarify the definition of overadjustment bias, and to distinguish overadjustment bias from unnecessary adjustment. Using simulations, we quantify the amount of bias associated with overadjustment. Moreover, we show that this bias is based on a different causal structure from confounding or selection biases. Overadjustment bias is not a finite sample bias, while inefficiencies due to control for unnecessary variables are a function of sample size.