Selection On Observables Only

Selection on observables means we assume differences come only from measured factors. We act like unmeasured things do not change the result.

Selection on observables posits that treatment assignment is independent of potential outcomes conditional on observed covariates; unobserved confounders are assumed absent. This identification strategy relies on measured covariates capturing all systematic differences influencing both assignment and outcomes.

A school district wants to know whether a new tutoring program raises test scores. Analysts compare students who enrolled in tutoring against those who did not, adjusting for grade level, prior GPA, and family income. If motivated parents systematically enroll their children and parental motivation is not measured, the apparent benefit of tutoring is inflated—the assumption that all relevant differences are captured by the measured variables is violated.

A health economist uses propensity-score matching on age, sex, comorbidity index, and insurance type to estimate the effect of a new antihypertensive on 5-year cardiovascular mortality in an administrative claims dataset. The study reports a statistically significant protective effect. However, medication adherence and lifestyle behaviors (diet, exercise) are unobserved in claims data and are correlated both with prescribing patterns (sicker, less adherent patients may be assigned the older drug) and with mortality. The conditional independence assumption—treatment ignorability given the observed adjustment set—is violated. A formal E-value calculation reveals that an unmeasured confounder with a relative risk of only 1.8 for both treatment assignment and outcome could fully explain the estimated effect, well within the plausible range for adherence-related confounding. Without an exclusion restriction or negative control outcome test, the backdoor adjustment remains incomplete and the reported estimate carries unobserved confounding contamination.

When we compare groups with the same measured traits, differences come from the treatment. Measured traits act like filters that make groups similar.

Observed covariates constrain assignment probabilities so that conditional on these covariates, treatment is asymmetrically independent of potential outcomes; the covariate set serves as a structural conditioning element. This weighting of conditional strata enforces an identification constraint by removing bias from measured confounders.

Collect more relevant measurements to reduce hidden differences. Use designs that compare similar people.

Augment with instrumental variables or panel methods to address hidden confounding and relax conditional independence. Employ sensitivity analysis to quantify robustness to unobserved biases.

Unmeasured confounders present; Poor covariate overlap; Modeling mis-specification

An adversarial analyst can deliberately select only favorable observable covariates into an adjustment set, creating the appearance of rigorous causal identification while leaving known unmeasured confounders unaddressed. This strategy allows a researcher or sponsor to report conditionally unbiased estimates that are in fact deeply confounded, since reviewers cannot easily audit what was omitted from the covariate set. Selective covariate disclosure is especially potent in proprietary datasets where outsiders cannot verify the completeness of the measured variable list.

Pre-register the full covariate selection protocol and the theoretical causal graph (DAG) prior to data collection so that omissions become auditable against a stated commitment. Pair observational estimates with sensitivity analyses (e.g., Rosenbaum bounds, E-values) to quantify how strong unmeasured confounding would need to be to overturn conclusions. Where feasible, supplement with a design-based identification strategy—instrumental variables, difference-in-differences, or regression discontinuity—to triangulate against the selection-on-observables assumption.