Robust Model-Based Clustering of Voting Records

TL;DR

This paper introduces a novel mixture model based on contaminated normal distributions to identify extreme voting patterns in U.S. Congressional records, effectively clustering binary data with potential outliers.

Contribution

It presents the first mixture model for binary data that captures extreme patterns using contaminated normal distributions, applied to voting record analysis.

Findings

Successfully identified extreme voting patterns in Congressional data

Demonstrated the model's ability to cluster binary data with outliers

First application of contaminated normal mixture model to binary voting data

Abstract

We explore the possibility of discovering extreme voting patterns in the U.S. Congressional voting records by drawing ideas from the mixture of contaminated normal distributions. A mixture of latent trait models via contaminated normal distributions is proposed. We assume that the low dimensional continuous latent variable comes from a contaminated normal distribution and, therefore, picks up extreme patterns in the observed binary data while clustering. We consider in particular such model for the analysis of voting records. The model is applied to a U.S. Congressional Voting data set on 16 issues. Note this approach is the first instance within the literature of a mixture model handling binary data with possible extreme patterns.