Semiparametric methods for the measurement of latent attitudes and the estimation of their behavioural consequences’, CEMMAP Working Paper CWP26/07

A. We model attitudes as latent variables that induce stochastic dominance rela-tions in (item) responses. Observable characteristics that affect attitudes can be incorpo-rated into the analysis to improve the measurement of the attitudes; the measurements are posterior distributions that condition on the responses and characteristics of each respon-dent. Methods to use these measurements to characterize the relation between attitudes and behaviour are developed and implemented. 1. Introduction. ‘Factor analysis ’ has a long history in the social sciences, and one use of factor analy-sis has been to measure latent characteristics of individuals. These latent characteristics are supposed to explain a variety of related behaviours, and interest is centered on how the assumption of the existence of a small number of underlying characteristics explains the cor