Categorical Response Data

Ben Jann

The term categorical response data refers to data for outcome variables whose values represent distinct categories as opposed to continuous quantities. Categorical variables are pervasive in political science. Examples are as diverse as party affiliation (“Democrat,” “Republican,” “other,” “none”), union membership (“yes,” “no”), form of government (“republic,” “monarchy,” “military dictatorship,” etc.), voter participation (“yes,” “no”), or confidence in the government (“a great deal,” “quite a lot,” “not very much,” “none at all”). Although examples for the collection of categorical data can probably be traced back as far as the ancient censuses in Egypt, it was not until the early 20th century that a systematic development of statistical methods for the analysis of categorical data began. The starting point was the work of Karl Pearson and G. Udny Yule, who debated over how best to analyze associations between categorical variables. Many fundamental contributions that prepared the ground for the emergence The ...

Users without subscription are not able to see the full content on this title. Please, subscribe or login to access all content on this website.