Dimensions in Congressional Voting

Abstract

While dimensional studies of congressional voting find a single, ideological dimension, regression estimates find several constituency and party dimensions in addition to ideology. I rescale several unidimensional studies to show their increased classification success over the null hypothesis that votes are not unidimensional. Several null hypotheses are explored. With these null hypotheses, 66%–75% of nonunidimensional roll call votes are nevertheless correctly classified by one dimension. After the rescaling, one dimension succeeds in correctly classifying 25%–50% of the votes, and second and third dimensions are important.

Factor analysis versus multi-dimensional scaling: binary choice roll-call voting and the US Supreme Court

“…In particular, our findings shed direct light on the controversy between Poole and Rosenthal (1984, 1991, on the one hand, and Clausen (1973) and Koford (1989Koford ( , 1991, on the other, over the dimensionality of Congressional voting. Our results show that Koford is right that MDS methods may overweight the first dimension in an attitude structure, but that the MDS methodology used by Poole and Rosenthal nonetheless provides a quite accurate representation of the dimensionality of legislative choice.…”

One-dimensionality and stability in legislative voting

“…Sound methods of dimensional analysis for roll-call votes, such as Poole-Rosenthal NOMINATE scoring, demonstrably achieve their advertised purpose of matching proximity between legislators with the probability of their voting alike. But do not expect the dimensions found thereby to serve other purposes (Koford 1989), and when those dimensions turn out to be one in number, do not infer single peakedness.…”

Selection and Influence: Interest Groups and Congressional Voting on Trade Policy

“…Although we use Poole and Rosenthal's 1997 D-NOMINATE scores to represent ideology, we are agnostic about arguments over whether they are a completely satisfactory representation of the dimensionality of congressional roll-call votes. (See, for example, the criticisms by Koford 1989;Poole, Rosenthal, and Koford 1991;and Heckman and Snyder 1997.) Scholars such as Hinich and Munger 1994, who insist that ideology is important generally, support the use of D-NOMINATE scores rather than interest group ratings, the only obvious alternative.…”