EcoSta 2021: Start Registration
View Submission - EcoSta2021
A0574
Title: Visualizing simultaneous uncertainty in Monte Carlo experiments Authors:  James Flegal - University of California - Riverside (United States) [presenting]
Dootika Vats - Indian Institute of Technology, Kanpur (India)
Galin Jones - University of Minnesota (United States)
Nathan Robertson - University of California - Riverside (United States)
Abstract: Monte Carlo experiments produce samples in order to estimate features of a given distribution. However, simultaneous estimation of means and quantiles has received little attention, despite being common practice. In this setting, we establish a multivariate central limit theorem for any finite combination of sample means and quantiles under the assumption of a strongly mixing process, which includes the standard Monte Carlo and Markov chain Monte Carlo settings. We build on this to provide a fast algorithm for constructing hyperrectangular confidence regions having the desired simultaneous coverage probability and a convenient marginal interpretation. The methods are incorporated into standard ways of visualizing the results of Monte Carlo experiments, enabling the practitioner to assess the reliability of the results more easily. We demonstrate the utility of this approach in various Monte Carlo settings, including simulation studies based on independent and identically distributed samples and Bayesian analyses using Markov chain Monte Carlo sampling.