During the last few years there has been an increasing interest in understanding the relationship between exchange-rate regimes and macroeconomic stability. Some recurrent policy questions are: (a) why do countries still choose fixed, nominal exchange-rate regimes 25 years after the abandonment of the Bretton Woods system? (b) do fixed exchange-rate regimes impose an effective constraint on monetary and fiscal behavior, thus lowering inflation rates over the long run? and (c) are exchangerate-based stabilization programs superior to money-based programs? This paper deals with the first question-the selection of the exchange-rate regime-from a politicaleconomy perspective. Why certain countries choose a particular type of exchange-rate regime is a highly relevant question. Why does Austria have a fixed exchange rate, for example, while the United Kingdom has a flexible one? Why has Argentina chosen a fixed exchange rate, while Chile has a flexible-cumbands system? More generally, in December 1992, why did 84 countries (out of the 167 reported in the IMF's International Financial Statistics) peg their currencies to a major currency or a currency composite? The theoretical discussion deals with the trade-off between credibility and flexibility, and it emphasizes the role of politics and institutions. In the empirical section I use a large cross-country panel data set to analyze the role of various factors, including political instability, in decid