Abstract
Classic methods of hypothesis testing are built through p-values. Introduced around 2020, e-values and e-processes are alternatives to p-values as measures of uncertainty, significance and evidence. They have statistical advantages over p-values, such as sequential anytime validity, post-hoc decision validity, multiple testing and robustness to dependence. We briefly introduce the theory of e-values and e-processes, and discuss their theoretical features and applications in several scientific areas.
Biography
Dr. Ruodu Wang is Tier-1 Canada Research Chair in Quantitative Risk Management and Professor of Actuarial Science and Quantitative Finance at the University of Waterloo. He received his PhD in Mathematics (2012) from the Georgia Institute of Technology, after completing his Bachelor (2006) and Master’s (2009) degrees at Peking University. He holds editorial positions in 8 leading journals in actuarial science, operations research, statistics, and economics, including Co-Editor of ASTIN Bulletin - The Journal of the International Actuarial Association and Co-Editor of the European Actuarial Journal. Among other international awards and recognitions, he is the first winner of the SOA Actuarial Science Early Career Award (2021) from the Society of Actuaries, and a Fellow of the Institute of Mathematical Statistics (elected 2022). His research papers are published in top journals across a wide range of scientific fields, such as the American Economic Review, the Annals of Statistics, the Journal of the Royal Statistical Society (Series B), Management Science, Operations Research, and the Proceedings of the National Academy of Sciences.
