This article proposes a structural approach to measuring the effects of electoral accountability. We estimate a political agency model with imperfect information in order to identify and quantify discipline and selection effects, using data on U.S. governors. We find that the possibility of reelection provides a significant incentive for incumbents to exert effort, that is, a disciplining effect. We also find a positive but weaker selection effect. According to our model, the widely used two-term regime improves voter welfare by 4.2% compared to a one-term regime, and better voter information about the effort of the governors would further increase voter welfare by up to 0.5%.