Natural experiments use policy changes to produce quasi-random variation in data

Evidence

One answer to these problems is to set up a natural experiment, that is, a situation in which the sociotechnical arrangements whose effect one wants to study are altered as a result of some event or circumstance “beyond the immediate control of the investigator” (McGinnis 1964). The typical case is one in which a change in government policy or legislation affects some members of a population but not others, creating a variation in the data that is random; or, if not random, at least unconnected or “orthogonal” to any unobservable factors that might be affecting the outcome one is trying to explain (Rosenzweig and Wolpin 2000, 828). — Philip Mirowski & Dieter Plehwe (eds.), The Road from Mont Pèlerin, 1936

Categorization

• DEFINE: Defines ‘natural experiment’ and the key identifying assumption of orthogonality to unobservable factors.
• XREF: connects to: Economic ‘natural experiments’ depend on prior policy programs, not nature — Philip Mirowski & Dieter Plehwe (eds.), The Road from Mont Pèlerin: The Making…, 1985; Natural quasi-experiments can separate media event effects from preexisting differences — John T. Jost and Jim Sidanius, Political Psychology, 1583; Natural experimental conditions allow rigorous causal tests of media effects (+4 more)

Broader Connections

• Economic ‘natural experiments’ depend on prior policy programs, not nature #expands (0.90) — Philip Mirowski & Dieter Plehwe (eds.), The Road from Mont Pèlerin, 1985
• Natural quasi-experiments can separate media event effects from preexisting differences #corroborates (0.85) — John T. Jost and Jim Sidanius, Political Psychology, 1583
• Natural experimental conditions allow rigorous causal tests of media effects #corroborates (0.80)
• Contingent events are non-random yet depend on aberrant chance conditions #qualifies (0.75) — John T. Jost and Jim Sidanius, Political Psychology, 4266