CEOs have become a topic of increasing scrutiny in economic research. Early studies on this topic inferred the presence of differentiation in CEOs’ abilities and managerial styles indirectly, examining changes in firm performance after exogenous events such as deaths or movements of managers across different firms affected their ability to manage.1 This summary describes recent empirical work that I have conducted to generate direct evidence on what top managers do, how they differ from one another, and whether these differences matter for firms’ performance.

The research touches upon different aspects of what CEOs do — ranging from day-to-day behavior to strategy setting. Ultimately, it strives to build new measurements of CEOs’ activities that are at the same time fine grained and scalable within and across countries. Given the intangible nature of leadership, this requires embracing an eclectic empirical approach, including developing new survey instruments, exploring previously untapped quantitative and textual data sources, and adopting machine learning methods to leverage rich and at times unstructured data.

This research has led to three broad findings. First, top managers vary considerably in what they do, both in terms of day-to-day behaviors (effort on the job, allocation of time across activities) and decision-making approaches (specifically, the formulation and execution of firm strategies). Second, CEOs also differ in terms of what they do not do, that is, the extent to which they allocate decision-making authority to other individuals in their organizations. Third, differences across CEOs in both activities and delegation are related to organizational performance, primarily due to matching effects. There isn’t one optimal way to be a CEO. What matters is the fit between what CEOs do (or do not do, in the case of delegation) and the specific needs of the firms that they run. This latter finding points to the importance of studying frictions in the market for CEOs, starting with imperfections in the selection of CEOs and in the way in which CEOs’ activity is monitored and