Probit Models for Ranking Data

摘要: In 1980, the American Psychological Association (APA) conducted an election in which five candidates (A, B, C, D, and E) were running for president voters asked to rank order all of candidates. Candidates A B are research psychologists, C is a community psychologist, D E clinical psychologists. Among those voters, 5738 gave complete rankings. These rankings considered here (Diaconis (1988)). Note that lower implies more favorable. Then average ranks received by A, 2.84, 3.16, 2.92, 3.09, 2.99, respectively. This means generally prefer candidate most, second, etc. However, make inferences on preferences candidates, modeling ranking data needed. Sect. 9.1 we consider model this takes into account covariates.