Rain, rain, go away: 194 potential exclusion‐restriction violations for studies using weather as an instrumental variable

Abstract

Instrumental variable (IV) analysis relies on the exclusion restriction—that the instrument only affects the dependent variable via its relationship with the independent variable and not via other causal routes. However, scholars generally justify the exclusion restriction based on its plausibility. I propose a method for searching for additional violations implied by existing social science studies. I show that the use of weather to instrument different independent variables represents strong prima facie evidence of exclusion‐restriction violations for all weather‐IV studies. A review of 289 studies reveals 194 variables previously linked to weather: all representing potential exclusion‐restriction violations. Using sensitivity analysis, I show that the magnitude of many of these violations is sufficient to overturn numerous existing IV results. I conclude with practical steps to systematically review existing literature to identify and quantify possible exclusion‐restriction violations when using IV designs.