My ongoing project focuses on methods for identifying and estimating the parameters of a dynamic game of elections with adverse selection, moral hazard, and strategic entry by candidates. The methods are applied to state gubernatorial election in the United States. In the game, candidates from two parties compete for office in each time period over an infinite horizon. Candidates have heterogeneous costs for expending effort to produce good outcomes in office. High competence candidates – those with zero costs of effort – are preferred by voters but also have a higher opportunity cost of running for office. The voters cannot perfectly observe candidate types or effort and instead observe a noisy outcome that is correlated with effort. Thus, the model presents a dynamic agency problem with moral hazard and adverse selection. The parameters of the model are estimated on gubernatorial elections in states with term limits. Parameter identification relies on the fact that only competent agents give high effort in their final term when there is no possibility of reelection. The estimation will allow us to quantify (1) the relative importance of electoral selection and accountability for explaining government performance, (2) the importance of ``scare-off” in terms of explaining entry by competent candidates and providing incentives for high performance by incumbents, (3) the impacts of counterfactual policy reforms such as a change in the electoral rule for reelecting incumbents or a policy that subsidizes part of the cost of running for office.