Skip navigation.
Home

Generic variable analysis: climbing the ladder of generality with social science data

TitleGeneric variable analysis: climbing the ladder of generality with social science data
Publication TypeConference Paper
Year of Publication2011
AuthorsSio, Lorenzo De, and Mark Franklin
Conference Name1st European Conference on Comparative Electoral Research
KeywordsGeneric concepts, HLM, ladder of generality, party support, vote propensity
Abstract

This paper attempts to provide a theoretical basis for the use of a set of procedures associated with the use of stacked datasets in the analysis of so-called “propensity to vote” (PTV) questions asked in increasing numbers of election surveys worldwide. These procedures make possible a shift in the conceptual level at which we think about party support, from the level of specific parties to the level of parties in general. The paper considers the the trade-offs involved in choosing a level of analysis and level of conceptualization appropriate to a particular research question. We will argue that these trade-offs should be explicitly considered by researchers who should not routinely settle on the default strategy of analyzing data at the level at which it was collected.

AttachmentSize
DeSio and Franklin.pdf255.96 KB