Replication data for: Computerized Adaptive Testing for Public Opinion Surveys

Survey researchers avoid using large multi-item scales to measure latent traits due to both the financial costs and the risk of driving up non-response rates. Typically, investigators select a subset of available scale items rather than ask- ing the full battery. Reduced batteries, however, can sharply reduce measure- ment precision and introduce bias. In this article, we present computerized adaptive testing (CAT) as a method for minimizing the number of questions each respondent must answer while preserving measurement accuracy and precision. CAT algorithms respond to individuals’ previous answers to select sub- sequent questions that most efficiently reveal respondents’ position on a latent dimension. We introduce the basic stages of a CAT algorithm and present the details for one approach to item-selection appropriate for public opinion research. We then demonstrate the advantages of CAT via simulation and em- pirically comparing dynamic and static measures of political knowledge. This replication file contains all files necessary for replicating the tables and figures in the paper. In addition, it contains a beta version of the R functions necessary for running a CAT algorithm, which is the basis of an S4 R package currently in development. Finally, we provide the code we developed for implementing our approach via web API. Improved documentation for both the R package and the API will be added to this archive as they are developed.