Home  >>  Archives  >>  Volume 16 Number 1  >>  st0428

The Stata Journal
Volume 16 Number 1: pp. 139-158



Subscribe to the Stata Journal
cover

Estimating polling accuracy in multiparty elections using surveybias

Kai Arzheimer
Johannes Gutenberg University
Mainz, Germany
arzheimer@politik.uni-mainz.de
Jocelyn Evans
University of Leeds
Leeds, UK
j.a.j.evans@leeds.ac.uk
Abstract.  Any rigorous discussion of bias in opinion surveys requires a scalar measure of survey accuracy. Martin, Traugott, and Kennedy (2005, Public Opinion Quarterly 69: 342–369) propose such a measure A for the two-party case, and Arzheimer and Evans (2014, Political Analysis 22: 31–44) demonstrate how measures Ai, B, and Bw for the more common multiparty case can be derived. We describe the commands surveybias, surveybiasi, and surveybiasseries, which enable the fast computation of these binomial and multinomial measures of bias in opinion surveys. While the examples are based on pre-election surveys, the methodology applies to any multinomial variable whose true distribution in the population is known (for example, through census data).
Terms of use     View this article (PDF)

View all articles by these authors: Kai Arzheimer, Jocelyn Evans

View all articles with these keywords: surveybias, surveybiasi, surveybiasseries, multinomial variables, surveys, survey bias

Download citation: BibTeX  RIS

Download citation and abstract: BibTeX  RIS