摘要：Transitions from authoritarianism and breakdowns of democracy have long been central puzzles for scholars of Latin American politics. Because structural explanations have proved to be weak, recent work has emphasised political agency . This strand of research is promising, but major questions remain unanswered: Who are the key actors driving regime change? How do their individual preferences affect transitions and breakdowns? This article focuses on three central members of the political elite: presidents, opposition leaders, and military commanders. These actors develop unique preferences about regimes and unique degrees of radicalism regarding their preferred policies; in turn, these preferences and radicalism affect the probabilities of regime change. Testing the argument in 20 nations between 1945 and 2010, we find that an average measure of preferences masks crucial distinctions in the chain of regime change. Transitions to a competitive regime are more likely when autocrats have low intrinsic commitments to dictatorship. The survival of democracies hinges on whether top military officials develop pro-democratic preferences. The role of executive preferences, by contrast, is moderated by the attachments and radicalism of opposition leaders. Next, we examine how structural contexts shape both preferences and political outcomes, finding that economic development shapes both the emergence of preferences and radicalism and their impacts on regime change. Our findings improve the validity of political agency theories and reconcile the roles of actors with the environments in which regimes emerge and fall.
