Estimating Economic Damages with Linear Regression and Bayesian Networks (Part 2)

In 2010, Robert M. Lloyd wrote, “In an ideal world, a court would be able to hear the evidence, estimate the plaintiff's damages, and quantify its own confidence that the estimate was accurate.” This article, the second in a two-part series, argues that Bayesian networks can move the legal world very close to Lloyd's ideal. Part 2 defines Bayesian networks, illustrates how Bayesian networks could have been used advantageously in a recent actual case, and posits that Bayesian networks are a highly effective tool for triers of fact to evaluate the fact and amount of damages with the “reasonable certainty” required by case law. Along the way, Part 2 challenges the popular mythology that point estimates offer higher certainty than value ranges.Part 1 of this paper can be found at "http://ssrn.com/abstract=3434046" http://ssrn.com/abstract=3434046