Theories of the structure of political belief systems typically conceive of them as networks of interrelated opinions, in which some beliefs are central and others are derived from these more fundamental positions. In this paper, we formally show how such structural features can be used to construct measures of belief centrality that are based on direct comparisons of relative positions of beliefs in a network of correlations. To demonstrate the usefulness of this method and contrast it with existing techniques, we examine belief networks we construct from the 2000 American National Election Study. While regression analyses of these data have been used to argue that political beliefs are organized around cultural schemas of parenting, our structural approach contradicts this interpretation. Instead, our results are broadly consistent with the conception of political identity as a heuristic device for acquiring attitudes. To search for possible heterogeneity, we then separately examine belief networks belonging to 44 different demographic subpopulations. These analyses indicate that belief systems of different groups vary in the extent to which they are organized, but rarely vary in the logic around which they are organized. While our analyses focus on political beliefs, techniques we introduce here can be applied to many other cultural domains.

Download: [PDF of working paper]

The measurement of shared cultural schemas is a central methodological challenge for the sociology of culture. Relational Class Analysis (RCA) is a recently developed technique for identifying such schemas in survey data. However, existing work lacks a clear definition of such schemas, leaving RCA’s accuracy largely unknown. Here, I build on the theoretical intuitions behind RCA to arrive at this definition. I demonstrate that shared schemas should result in linear dependencies between survey rows—the relationship usually measured with Pearson’s correlation. I thus modify RCA into a “Correlational Class Analysis” (CCA). When I compare the two methods using a broad set of simulations, results show that CCA is reliably more accurate at detecting shared schemas than RCA, even in scenarios that substantially violate the assumptions behind CCA. I find no evidence of theoretical settings where RCA would be more accurate. I then revisit a prior RCA analysis of the 1993 GSS musical tastes module. While RCA had partitioned these data into three schematic classes, CCA partitions them into four. I compare these results with a multiple groups analysis in SEM, finding that CCA’s partition yields greatly improved model fit. I conclude with a parsimonious framework to guide future work.

Download: [PDF of working paper] and [R package]

We predict that people with different political orientations will exhibit systematically different levels of political homophily, the tendency to associate with others similar to oneself in political ideology. Research on personality differences across the political spectrum finds that both more conservative and more politically extreme individuals tend to exhibit greater orientations towards cognitive stability, clarity, and familiarity. We reason that such a “preference for certainty” may make these individuals more inclined to seek out the company of those who reaffirm, rather than challenge, their views. Since survey studies of political homophily face well-documented methodological challenges, we instead test this proposition on a large sample of politically engaged users of the social networking platform Twitter, whose ideologies we infer from the politicians and policy non-profits they follow. As predicted, we find that both more extreme and more conservative individuals tend to be more homophilous than more liberal and more moderate ones.

Download: [PDF of working paper]