We study the determinants of patent suits and their outcomes over the period 1978-1999 by linking detailed information from the U.S. patent office, the federal court system, and industry sources. The probability of being involved in a suit is heterogeneous, being much higher for valuable patents and for patents owned by individuals and smaller firms. Thus the patent system generates incentives, net of expected enforcement costs, that differ across inventors. Patentees with a large portfolio of patents to trade, or having other characteristics that encourage ¿cooperative¿ interaction with disputants, more successfully avoid court actions. At the same time, key post-suit outcomes do not depend on observed characteristics. This is good news: advantages in settlement are exercised quickly, before extensive legal proceedings consume both court and firm resources. But it is bad news in that the more frequent involvement of smaller patentees in court actions is not offset by a more rapid resolution of their suits. However, our estimates of the heterogeneity in litigation risk can facilitate development of private patent litigation to mitigate this adverse effect of high enforcement costs.