Activity Number:
|
541
- Recent Progresses in Bayesian Inference in Large Parameter Spaces: Jayanta K. Ghosh Memorial Session
|
Type:
|
Invited
|
Date/Time:
|
Wednesday, July 31, 2019 : 2:00 PM to 3:50 PM
|
Sponsor:
|
Memorial
|
Abstract #300433
|
Presentation
|
Title:
|
Leveraging the Order-Dependence of Predictive Recursion for Uncertainty Quantification About a Mixing Density
|
Author(s):
|
Ryan Martin* and Vaidehi Dixit
|
Companies:
|
North Carolina State University and North Carolina State University
|
Keywords:
|
mixture model;
nonparametric;
density estimation;
deconvolution;
uncertainty quantification;
inverse problem
|
Abstract:
|
Estimation of the mixing distribution based on data coming from a mixture model is a challenging problem, and quantification of certainty is all the more difficult. In this talk, I will present a strategy that leverages the order-dependence of Newton's predictive recursion estimator to construct a permutation-based posterior distribution and discuss -- theoretically and empirically -- its uncertainty quantification properties.
|
Authors who are presenting talks have a * after their name.