Elections are the core of the political process in democratic systems. How do people vote? The study of voting behavior has seen a shift from theories centered on social groups to theories centered on individuals. One of the most prominent expectations has been the individualization of politics, for which individuals (leaders) increased their importance for vote choice at the expense of groups (parties). However, empirical results provide little support for it. In this paper, I assemble the largest dataset ever used to analyze the relative importance of parties and leaders for voting behavior, spanning from 1961 to 2019 with more than 230,000 unique respondents. Furthermore, I propose a statistical model that controls for observed and unobserved heterogeneity at the country, election, and party levels.