Learning by Suing: Structural Estimates of Court Errors in Patent Litigation

This paper presents structural estimates of the probability of validity, and the probability of Type I and Type II errors by courts in patent litigation. Patents are modeled as uncertain property rights, and implications of the model are tested using stock market reactions to patent litigation decisions. The estimation quantifies beliefs about patent validity and court errors in a Bayesian context. I estimate that the underlying beliefs about validity range from 0.6 to 0.7 for litigated patents. Market beliefs about courts show that Type I errors (finding a valid patent invalid) occur very frequently–an estimated probability of 0.45. However, Type II errors (finding an invalid patent valid) occur with near zero probability. Additional implications of the model address patent value. My results are the first structural estimates of court errors. Additionally, this study is the first to perform event studies on patent litigation.