Research
Working Papers
How Do Expectations Affect Learning About Fundamentals? Some Experimental Evidence (with Nikhil Krishna, and Jarel Tang)
Often, individuals' optimal actions depends on external fundamentals, and they cannot separately identify the effect of these fundamentals and their own actions on output. Many individuals have incorrect beliefs about their own ability. Heidhues et al. (2018) characterise overconfident and underconfident individuals' equilibrium beliefs and learning process in these situations. Counter-intuitively, they argue that learning makes overconfident agents worse off - their belief about fundamentals gets less accurate, causing them to take more and more sub-optimal actions. We carry out the first experimental test of their theory. Subjects take incorrectly-marked tests, and we measure how they learn about the marker's accuracy (the fundamental) over time. We use machine learning to identify heterogeneous effects. Overconfident subjects have lower beliefs about the fundamental, as Heidhues et al. predict, and thus would make sub-optimal decisions. But we find no evidence it is because of how they learn.
How Do Expectations Affect Learning About Fundamentals? Some Experimental Evidence (with Nikhil Krishna, and Jarel Tang)
Often, individuals' optimal actions depends on external fundamentals, and they cannot separately identify the effect of these fundamentals and their own actions on output. Many individuals have incorrect beliefs about their own ability. Heidhues et al. (2018) characterise overconfident and underconfident individuals' equilibrium beliefs and learning process in these situations. Counter-intuitively, they argue that learning makes overconfident agents worse off - their belief about fundamentals gets less accurate, causing them to take more and more sub-optimal actions. We carry out the first experimental test of their theory. Subjects take incorrectly-marked tests, and we measure how they learn about the marker's accuracy (the fundamental) over time. We use machine learning to identify heterogeneous effects. Overconfident subjects have lower beliefs about the fundamental, as Heidhues et al. predict, and thus would make sub-optimal decisions. But we find no evidence it is because of how they learn.
Other Projects
Forecasting the Computerisability of Tasks (with Shruthi Prabakhar and Rob Axtell)
We construct the first dataset of all firms trying to computerise tasks, and of the current computerisability of types of task. We use this to build and validate a dynamic network model to forecast the computerisability of different types of task.
Forecasting the Computerisability of Tasks (with Shruthi Prabakhar and Rob Axtell)
We construct the first dataset of all firms trying to computerise tasks, and of the current computerisability of types of task. We use this to build and validate a dynamic network model to forecast the computerisability of different types of task.