Abstract
Ideological scales derived from policy position items are prevalent in political psychology and behavioral research. However, the underlying spatial assumptions of these scales are rarely scrutinized. This study investigates how assumptions about the dimensionality of the latent ideological space can significantly impact empirical estimates, even when using the same data from the same respondents. Through a comprehensive literature review and statistical simulations using data from the ANES, we demonstrate that the optimal number of latent ideological dimensions increases without bound as researchers include additional items for analysis. At the same time, nearly all latent ideological factors found within same attitude set are sizably and positively correlated with one another. In light of these findings, we propose an alternative modeling framework that seeks to reconcile unidimensional and multi-dimensional aspects of mass ideology. Our Bayesian hierarchical latent variable approach simultaneously estimates mass ideology as a higher-level, uni-dimensional expression of correlated, lower-level, multi-dimensional building blocks. This approach enables researchers to assess whether particular socio-demographic or psychological predictors, such as income, gender, or egalitarianism, are consistently related to specific sub-dimensions (e.g., economic, socio-cultural, racial ideology) or instead a generalized, uni-dimensional representation thereof. Our results underscore the potential value of this approach, offering insights into the unique characteristics of different ideological factors and their overarching parent dimension.
Philip Warncke
Post-doctoral fellow in Political Science
Philip Warncke is a recent doctoral graduate from the University of North Carolina at Chapel Hill. Philip studies mass belief systems, particularly how to measure and compare them, as well as their consequences for political outcomes.