You are here
Theoretical and Applied Data Science Lunch-n-learn
Presenter: Daniel Nettleton
Title: Introduction to Uncertainty Quantification for Predictions
Abstract: Our D4 TRIPODS proposal included a section on uncertainty-associated risks to the dependable data-driven lifecycle. This talk will introduce some of the ideas mentioned in the proposal related to quantifying uncertainty in predictions. Some methods for generating prediction intervals and predictive distributions will be discussed. We will focus on nonparametric approaches, including uncertainty quantifications based on conformal, out-of-bag, and cross-validation techniques.
Bio: Dan Nettleton is the Laurence H. Baker Endowed Chair, Distinguished Professor, and Chair of the Department of Statistics at Iowa State University. Dan also serves as Director of the Laurence H. Baker Center for Bioinformatics and Biological Statistics. Nettleton conducts research on statistical methods for the design and analysis of high-dimensional biological datasets. Example data types include transcriptomic data from microarrays or RNA-sequencing, microbiome data, genomic data for use in genome-wide association studies, and data on complex phenotypes. Since joining Iowa State University in 2000, Nettleton's work has been heavily influenced by numerous collaborations with leading plant and animal scientists who seek to understand the functions of genes in biological systems and to learn how genotype and environment interact to shape important phenotypes. Nettleton also works on the development of statistical learning methodology and has enjoyed applying such methods to problems in sports analytics. Nettleton teaches statistics courses, advises graduate student research, and serves on many student committees, both within the Department of Statistics and for students from a variety of other departments at Iowa State.
After the presentation, there will be a short time for discussion and questions afterwards. Please feel free to bring your lunch!