Please note, due to scheduled maintenance online transactions will not be possible between 08:00 and 12:00 BST, on Sunday 17th February 2019 (03:00-07:00 EDT, 17th February, 2019). We apologise for any inconvenience
Opinion surveys often employ multiple items to measure the respondent’s underlying value, belief, or attitude. To analyze such types of data, researchers have often followed a two-step approach by first constructing a composite measure and then using it in subsequent analysis. This paper presents a class of hierarchical item response models that help integrate measurement and analysis. In this approach, individual responses to multiple items stem from a latent preference, of which both the mean and variance may depend on observed covariates. Compared with the two-step approach, the hierarchical approach reduces bias, increases efficiency, and facilitates direct comparison across surveys covering different sets of items. Moreover, it enables us to investigate not only how preferences differ among groups, vary across regions, and evolve over time, but also levels, patterns, and trends of attitude polarization and ideological constraint. An open-source R package, hIRT, is available for fitting the proposed models.
Email your librarian or administrator to recommend adding this journal to your organisation's collection.