Christopher H. Achen

Let's Put Garbage-Can Regressions and Garbage-Can Probits Where They Belong

Many social scientists believe that dumping long lists of explanatory variables into linear regression, probit, logit, and other statistical equations will successfully “control” for the effects of auxiliary factors. Encouraged by convenient software and ever more powerful computing, researchers also believe that this conventional approach gives the true explanatory variables the best chance to emerge. The present paper argues that these beliefs are false, and that without intensive data analysis, linear regression models are likely to be inaccurate. Instead, a quite different and less mechanical research methodology is needed, one that integrates contemporary powerful statistical methods with deep substantive knowledge and classic data—analytic techniques of creative engagement with the data.

Statistics as If Politics Mattered: A Reply to Fowler and Hall

Anthony Fowler and Andrew Hall question both the statistical validity and the broader significance of our analysis of the electoral impact of shark attacks along the Jersey Shore in 1916. Setting aside the politics and history of the Progressive period, they focus on methodological considerations, carrying out an extensive set of tests intended to cast all-purpose doubt on our interpretation of the electoral evidence. However, we show that this style of analysis leads them not just into historical misjudgments but into statistical lapses as well. Correcting those missteps, and setting aside the substantial share of their evidence that has no bearing on our argument, leaves our conclusions handsomely supported. In the end, we argue, statistical calculations ignoring the relevant politics and history contribute little to scientific understanding.

Government for the People: A Reply to the Symposium

ABSTRACT If representative democracy is not about elected officials responding directly to voters’ preferences, and if the voters do a poor job of voting their interests in referendums, then what is democracy about? In our view, a satisfactory theory of democracy would focus normatively on the social identities and political interests of citizens rather than on their expressed policy preferences, and empirically on the ability of organized or attentive groups to get those identities and interests effectively recognized and acted on in the governmental process. A group-theoretic version of democratic theory along these lines would dispense with the most important illusions of the conventional “folk theory” of democracy. However, much hard work remains to clarify how actual democracies make policy and to construct a wise normative standard—inspirational but not innocent—against which they can be judged.