This project aims to build a comprehensive dataset of all disciplinary actions taken by a state medical board against a physician to answer questions such as 1) What are the characteristics of physicians that get disciplined? What are the differences based on the severity of the disciplinary action? 2) How does disciplinary action influence future physician behavior? 3) How do physician networks influence misconduct? This project involves collecting data from the websites of state medical boards to create a longitudinal dataset of disciplinary actions taken against physicians. Most websites contain high-level information in a table format, but more important details are often embedded into PDF files that describe the reasons for the disciplinary action. For example, sometimes disciplinary actions are quite serious for infractions such as fraud or misprescribing of opiates, and the PDF files provide much of this detail.
