In epidemiology, the E-value is best described as:

• A. The maximum strength of unmeasured confounding that could not explain away the observed association.
• B. A measure of study precision unrelated to confounding.
• C. The minimum strength of unmeasured confounding needed to explain away the observed association.
• D. A metric that directly adjusts the effect estimate for unmeasured confounding.

Answer: (C)

The question tests how robust an observed association is to unmeasured confounding. The E-value captures the minimum strength that an unmeasured confounder would need to have with both the exposure and the outcome (beyond the measured covariates) to completely explain away the observed association.

A larger E-value means the result is more resistant to the idea that an unmeasured confounder could account for it. It does not adjust the effect estimate itself, and it isn’t a direct measure of study precision. It’s a sensitivity-analysis quantity that tells you how strong a hidden confounder would have to be to nullify the finding.

For example, if you observe a risk ratio of 2.0, the E-value is roughly 2 + sqrt(2*(2-1)) ≈ 3.41. That implies an unmeasured confounder would need to have associations of at least about 3.4 with both the exposure and the outcome to explain away the association, conditional on the measured covariates. If such a confounder is implausible, the result is more robust to unmeasured confounding.