Algorithms are increasingly used to make important decisions that impact people. Often these algorithms use a lot of data that could contain information about legally protected categories like sex or race. We need to know whether an algorithm is discriminating in an unjust way, but if the algorithm is computationally complex and depends on many variables this could be difficult to determine. Dr. Loftus develops statistical concepts and tools to help people address problems like this transparently and precisely. He has used causal modeling to shed light on issues like intersectional fairness and the drawbacks of measuring discrimination based on only direct dependence.