Blackwell Seminar: Statistics and the law: Causal inference, forensic analysis, and systemic bias in the criminal justice system
Seminar presented by Maria CuellarThis talk introduces the emerging field of statistics and the law. Attorneys and other legal actors often make statistical arguments, explicitly or implicitly. It is crucial that statisticians examine how statistics should be used and make recommendations about how to avoid the misuse of statistics in the law.
This misuse can take several forms. For example, it might consist of answering the wrong question. I consider how this sort of misuse can arise in civil cases, when attorneys use forecasting (what is the probability of an outcome given an exposure?) when they should be using attribution (what is the probability that an outcome was caused by an exposure?) to make a causal claim. Quite differently, misuse could arise in criminal cases, when the determination of guilt depends on subjective forensic methods. Finally, there is a role for statisticians to play in formalizing how contextual bias emerges from a misuse of statistics in forensic science and showing that it leads to downstream bias in the entire system.
The misuse of statistics has obvious social impacts, such as miscarriages of justice and errors of impunity. On a broader social level, such errors can lead to the mistrust in the criminal justice system, especially by populations that are overrepresented in the system. In short, this is a field in which statisticians can have a real, positive impact on society. I argue in this talk that aside from its obvious social importance, statistics and the law also raises novel and interesting statistical questions. In particular, this field prompts us to (1) distinguish among different causal parameters and study how best to estimate them; (2) compare and combine subjective and objective methods; and (3) examine how bias produced in forensic analysis is proliferated within the criminal justice system.
Details on the Blackwell Seminar can be found here.
