Mark J. Schervish received his Ph.D. from the University of Illinois at Urbana-Champaign in 1979 and has been a member of the faculty in the Deapartment of Statistics at Carnegie Mellon University since then. Dr. Schervish has taught mathematics, probability, and statistics to students in a wide variety of fields including computational finance.

Dr. Schervish has published applied, methodological, theoretical, and philosophical research papers as well as textbooks and research monographs. He is noted for his work in the foundations of inference and Bayesian statistics. He has served on editorial boards of top statistical journals and is a fellow of the American Statistical Association and of the Institute of Mathematical Statistics.

In his spare time, Dr. Schervish enjoys running, classic rock, and classic literature. He is married and has two children.

By this expert

Time Series Forecasting: Model Evaluation and Selection Using Nonparametric Risk Bounds

Paper Grantee paper | | Nov 2012

We derive generalization error bounds — bounds on the expected inaccuracy of the predictions — for traditional time series forecasting models.