Tae Hyun Kim (Lowell)

Negative Control Outcome (NCO)

1 min read #causal-inference#proximal

Definition

An NCO is an outcome variable guaranteed a priori to be unaffected by the treatment’s causal influence, yet still cast in the shadow of the same confounder UU. By contrast, an NCE (negative control exposure) is an exposure with no causal effect on the outcome. If the “apparent effect” on an NCO is nonzero → a signal of unmeasured confounding (detection) → correct for it via proximal methods.

Intuitive Understanding

The canary in the coal mine — if something that should not move does move, it means confounding control has failed. Given enough NCOs, their pervasiveness lets you reconstruct UU in reverse.

Key Papers

  • Lipsitch, Tchetgen Tchetgen & Cohen, “Negative controls”, Epidemiology 21(3), 2010
  • Shi, Miao & Tchetgen Tchetgen, negative controls / proximal review, 2020
  • Related prior work: Zhou et al. 2024 Biometrika; Zheng–Franks 2023 JASA

Local graph