According to both central bankers and economic theory, anchored in‡ation expectations are key to successful monetary policymaking. Yet, we know very little about the determinants of those expectations. While policymakers may take some comfort in the stability of long-run in‡ation expectations, the latter is not an inherent feature of the economy. What does it take for expectations to become unanchored? We explore a theory of expectations formation that can produce episodes of unanchoring. Its key feature is state-dependency in the sensitivity of long-run in‡ation expectations to short-run in‡ation surprises. Price-setting agents act as econometricians trying to learn about average long-run in‡ation. They set prices according to their views about future infl‡ation, which hence feed back into actual in‡ation. When expectations are anchored, agents believe there is a constant long-run in‡ation rate, which they try to learn about. Hence, their estimates of long-run in‡ation move slowly, as they keep adding observations to the sample they consider. However, in the spirit of Marcet and Nicolini (2003), a long enough sequence of in‡ation suprises leads agents to doubt the constancy of long-run in‡ation, and switch to putting more weight on recent developments. As a result, long-run in‡ation expectations become unanchored, and start to react more strongly to short-run in‡ation surprises. Shifts in agents’views about long-run in‡ation feed into their price-setting decisions, imparting a drift to actual in‡ation. Hence, actual in‡flation can show persistent swings away from its long-run mean. We estimate the model using actual in‡ation data, and only short-run in‡ation forecasts from surveys. The estimated model produces long-run forecasts that track survey measures extremely well. The estimated model has several uses: 1) It can tell a story of how in‡ation expectations got unhinged in the 1970s; it can also be used to construct a counterfactual history of infl‡ation under anchored long-run expectations. 2) At any given point in time, it can be used to compute the probability of in‡ation or de‡ation scares. 3) If embedded into an environment with explicit monetary policy, it can also be used to study the role of policy in shaping the expectations formation mechanism. Joint with Carlos Carvalho (PUC-Rio), Stefano Eusepiz (Federal Reserve Bank of NY), and Bruce Preston (The University of Melbourne).