Measuring Liberal/Conservative Voting Tendencies among U.S. Senators

Each year, the National Journal examines roll-call voting records for United States Congress, and groups topical voting records into three categories: economic, social, or foreign. This Rasch analysis attempted to measure liberal versus conservative voting tendencies based on 2011 voting records. Considering the House of Representatives consists of 435 members and the Senate consists of 100 members, for convenience, only U.S. Senators were investigated.

In total, 235 Senate voting records were registered in 2011. Many of these votes involved noncontroversial issues or topics that did not invoke ideological distinctions and thus, were removed from the dataset. In total, 97 votes appeared to fall along party lines and were selected as the basis for this analysis. These votes were parsed into the three aforementioned categories.

In order to analyze the data, it was necessary to first create two distinct data sets, one for senators who identified themselves as "Democrat" (n=51) and one for senators who identified themselves as "Republican" (n=47). Measures of conservative/liberal voting behaviors were discerned relative to members of one's own political party. This data parsing allowed two questions to be investigated: Among all Republican senators, who is the most/least likely to provide a conservative vote? And among all Democratic senators, who is the most/least likely to provide a liberal vote?

The National Journal data set provides counts of liberal versus conservative votes for each of the topical categories. This information alone is not useful for a Rasch analysis. However, with a rather novel recoding schema a useful data set can be prepared. For example, suppose a Republican senator placed 79 conservative votes and 16 liberal votes on foreign issues. This senator would provide a conservative vote on foreign issues at a ratio of about 5:1. Thus, simply assigning a value of 5 can serve as a useful proxy for the magnitude of conservative voting on topics of this nature. This recoding schema was repeated for every senator in both data sets until a useful data set was constructed. All data were recoded into values ranging from 1 to 9, with ratios exceeding 9 being truncated to 9.

Finally, person calibrations were produced for both Republicans and Democrats. Logits values were then rescaled onto a continuum ranging from 1-10 for easy interpretation. Results are presented in Tables 1 and 2.

Political scientists often refer to a political spectrum that ranges from the far liberal left to the far conservative right. Where one's views fall along this spectrum likely will determine the extent to which common ground can be established between individuals from opposing political parties. As demonstrated in this analysis, Rasch measurement can help empirically present one's views along this political spectrum. Senators with the highest measures are typically more polarizing in their views, whereas persons with lower measures are more likely to entertain views from the opposing party. Information gleaned from analyses such as this one can be useful for: identifying individuals with a voting record that likely will (or will not) resonate well with voters; identifying the extent to which legislators' votes are consistent with their political platforms; comparing the voting records/political views of legislators from the same state; identifying which individuals are likely to filibuster a bill if given the opportunity; predicting how various legislators will vote on a highly partisan issue; predicting the productivity of various congressional subcommittees based on its panel of members, etc.

Table 1. Conservative Voting Tendencies for Republican Senators

Table 2. Liberal Voting Tendencies for Democratic Senators

Kenneth D. Royal
University of Kentucky

Measuring Liberal/Conservative Voting Tendencies among U.S. Senators. Kenneth D. Royal … Rasch Measurement Transactions, 2012, 26:2 p. 1366-7

Rasch Publications
Rasch Measurement Transactions (free, online)	Rasch Measurement research papers (free, online)	Probabilistic Models for Some Intelligence and Attainment Tests, Georg Rasch	Applying the Rasch Model 3rd. Ed., Bond & Fox	Best Test Design, Wright & Stone
Rating Scale Analysis, Wright & Masters	Introduction to Rasch Measurement, E. Smith & R. Smith	Introduction to Many-Facet Rasch Measurement, Thomas Eckes	Invariant Measurement: Using Rasch Models in the Social, Behavioral, and Health Sciences, George Engelhard, Jr.	Statistical Analyses for Language Testers, Rita Green
Rasch Models: Foundations, Recent Developments, and Applications, Fischer & Molenaar	Journal of Applied Measurement	Rasch models for measurement, David Andrich	Constructing Measures, Mark Wilson	Rasch Analysis in the Human Sciences, Boone, Stave, Yale
in Spanish:	Análisis de Rasch para todos, Agustín Tristán		Mediciones, Posicionamientos y Diagnósticos Competitivos, Juan Ramón Oreja Rodríguez

Forum

Rasch Measurement Forum to discuss any Rasch-related topic

Go to Top of Page
Go to index of all Rasch Measurement Transactions
AERA members: Join the Rasch Measurement SIG and receive the printed version of RMT
Some back issues of RMT are available as bound volumes
Subscribe to Journal of Applied Measurement

Go to Institute for Objective Measurement Home Page. The Rasch Measurement SIG (AERA) thanks the Institute for Objective Measurement for inviting the publication of Rasch Measurement Transactions on the Institute's website, www.rasch.org.

The URL of this page is www.rasch.org/rmt/rmt262e.htm,

Website: www.rasch.org/rmt/contents.htm,