Policy Responsiveness or Families of Nations? The Between-Country Relationship of Public Opinion and Social Welfare Spending

Abstract

This paper reports the results of a replication of the work of Brooks and Manza, ‘Social Policy Responsiveness in Developed Democracies’ published in 2006 in the American Sociological Review. The paper finds that they utilized an interaction term but excluded the main effect of one of the interacted variables. This model specification has specific theoretical and statistical implications, namely that the omitted main effect variable has no correlation with the error term from their regression; theoretically speaking this means that all unobserved historical, cultural and any other characteristics distinguishing liberal democratic welfare regimes from others can be accounted for with a handful of quantitative measures. Using replicated data the paper finds that the Brooks and Manza models fail these assumptions. A sensitivity analysis using over 800 regressions with different configurations of variables confirms this. In 99.5% of the cases, addition of the main effect removes their empirical findings completely. A theoretical discussion illuminates why the paper’s findings are not surprising. The paper provides a reminder that models must match theories.