2026/04/06 by Carl Muller Crepon, Nils‐Christian Bormann · 2 voices
Social Sciences · #Aggregate (composite) #Aggregate data #Culture, Economy, and Development Studies #Electoral Systems and Political Participation #Ethnic group #Political Conflict and Governance #Pooling #Regression #Regression analysis #Selection (genetic algorithm) #Voting
paper · pdf · doi:10.1017/s0003055426101579
published in American Political Science Review, 1-19 (Cambridge University Press)
openalex created_date 2026/03/20 · openalex publication_date 2026/04/06 · openalex updated_date 2026/08/05
Ethnicity is an important cleavage in Africa, yet its influence on voting is contested. Selection biases from restricted choice sets complicate micro-level analyses, while ecological inferences and unobserved confounders hamper meso and macro-level approaches. Our new Covoting Regression (CVR) tackles several of these challenges. It estimates the effect of coethnicity on the probability that pairs of voters covote for the same party while conditioning on other shared characteristics. Thereby, CVR mirrors the micro-foundations of aggregate indicators such as the Herfindahl-Hirschman concentration index. We analyze Afrobarometer surveys from 28 countries and estimate that coethnicity increases covoting intentions between respondents by 17 percentage points. Politically relevant groups and covoting for ethnic parties drive this estimate, which is consistent across institutionally diverse countries and at least four times larger than that of other cleavages. The CVR addresses key issues in studying electoral consequences of socio-economic cleavages and bridges gaps between levels of analysis.