Voters that come of age at roughly the same time share common influences because of the specific political context during their formative years. We can therefore assume the errors in a model explaining their political behavior to be dependent. Recent advances in social statistical analysis of age-period-cohort (APC) effects propose the use of hierarchical modeling in combination with repeated cross-sectional survey design to solve this problem. We apply these random-intercept models to assess the impact of the political context on the development of generational turnout patterns, assuming that cohorts that grew up in a highly-politicized context have a higher propensity to turn out to vote despite of any age or period effects.
- Cohort analysis
- Political socialization
- mixed generalized linear modeling