unobservables
Variables affecting an outcome that the researcher cannot measure; controlling for them is the central concern of much modern econometrics.
As defined in James Heckman on Facts, Evidence, and the State of Econometrics
Where it comes up · 1
Most important claims · 2 of 2Search all claims for “unobservables” →
- The credibility revolution reduced bias but became obsessed with controlling for unobservables without asking what is actually being estimated, trading economic interpretability for statistical credibility, so its results identify hard-to-interpret statistical artifacts that cannot answer the structural economic questions needed for policy.James Heckman on Facts, Evidence, and the State of Econometrics
- Randomization can be understood as a special case of an instrumental variable: it moves people toward treatment or control while assuming it balances unobservables across the two groups, so an experiment is one type of instrument rather than a fundamentally different method.James Heckman on Facts, Evidence, and the State of Econometrics