Studying Dynamics in Legislator Ideal Points: Scale Matters

Research designs that call for the estimation of time trendsin legislator ideal points must allow for changes in underlyingpolicy spaces. Simply put, a set of legislator ideal pointsfrom one such space cannot necessarily be compared with a setof ideal points from another. Rothenberg and Sanders's (2000,American Journal of Political Science 44:316–325) analysisof shirking in Congress does not internalize this point insofaras it assumes that legislator ideal points from adjoining congressionalsessions lie in a common space. While it may be the case thatmembers of Congress shirk ideologically when approaching retirement,the regression estimates at the heart of Rothenberg and Sandersneither support this possibility nor constitute evidence againstit.