Arguing for a Negligible Effect

Political scientists often theorize that an explanatory variable shouldhave “no effect ” and support this claimbydemonstrating that its coefficient’s estimate is not statistically significant. This empirical argument is quite weak, but I introduce applied researchers to simple, powerful tools that can strengthen their arguments for this hypothesis. With several supporting examples, I illustrate that researchers can use 90 % confidence intervals to argue against meaningful effects and provide persuasive evidence for their hypothesis. Political scientists often theorize that particularvariables shouldnotmatter.1 Fearon (1994) arguesthat (observable) military strength has no direct effect on bargaining once an international crisis begins. Svolik (2008) suggests that economic development does not affect the timing of authoritarian reversals. Fearon and Laitin (2003) contend that ethnic and religious diver-sity do not make civil wars more likely. Kam and Palmer (2008) propose that education has no effect on political participation. These authors are not alone. On average, more than one article per issue of the American Politica