Each year many varied interest groups rate members of Congress. These ratings may be regarded as preferential choice data because they indicate the degree of approval of the members' voting records. Applying multidimensional unfolding to the ratings of U.S. senators for 1969-1978 produces one common evaluative dimension that accounts for approximately 80 percent of the variance. The ten configurations were fitted together so that senators and interest groups could be tracked across time. The large majority of senators and interest groups are stable on the identitied dimension over time with the exception that senators up for election tend to change position and become more ambiguous.
No takes yet. Share an insight, caveat, or question.
Keith T. Poole (1981) studied this question.
Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context: