On Models for Categorical Dependent Variables

• Elff, Martin. 2022. "Much Ado About Not Very Much? Clarifying the Confusion about Models for Categorical Dependent Variables".

Abstract:

Models for categorical dependent variables, such as turnout, party choice, or partisanship have eluded scholars for decades. Their parameters are often difficult to interpret and do not lend themselves easily to an intuitive understanding. Yet, the concepts and patterns of inference that work will within the framework of linear regression cannot easily transferred to models for categorical dependent variables. The paper discusses two instances where attempts to do this leads to misleading methodological recommendations.

• It should be noted that in its current state the paper is quite incomplete. Its argumentation is currently rather formal-mathematical, while its practical and empirical implications need to be further fleshed out.