| Abstract: | Although left–right items are a standard tool of publicopinion research, there is little agreement about the optimalresponse format. Two disputes can be identified in the literature:(1) whether to provide respondents with a small or large numberof answer categories, and (2) whether or not to administer theresponse scale including a midpoint. This study evaluates theperformance of the 101, 11, and 10-point left–right scales,which directly speak to the two disputed aspects of measuringthe left–right dimension. Drawing on data from a splitballot multitrait multimethod experiment carried out in a methodologicalpretest to the German Socio-Economic Panel (SOEP), the analysisshows that the choice of a response format makes a differencein terms of data quality: the 11-point left–right scaleproduces the highest validity of left–right data closelyfollowed by the 10-point scale. Moreover, an application fromelectoral research illustrates that the choice of response formatsaffects substantive interpretations about the nature of theleft–right dimension. Since all three scales perform aboutequally well in terms of reliability and the ease of administration,the findings suggest that the 11-point left–right scaleshould be used in survey research. |
