Inference from Iterative Simulation Using Multiple Sequences

Abstract

The Gibbs sampler, the algorithm of Metropolis and similar iterative simulation methods are potentially very helpful for summarizing multivariate distributions. Used naively, however, iterative simulation can give misleading answers. Our methods are simple and generally applicable to the output of any iterative simulation; they are designed for researchers primarily interested in the science underlying the data and models they are analyzing, rather than for researchers interested in the probability theory underlying the iterative simulations themselves. Our recommended strategy is to use several independent sequences, with starting points sampled from an overdispersed distribution. At each step of the iterative simulation, we obtain, for each univariate estimand of interest, a distributional estimate and an estimate of how much sharper the distributional estimate might become if the simulations were continued indefinitely. Because our focus is on applied inference for Bayesian posterior distributions in real problems, which often tend toward normality after transformations and marginalization, we derive our results as normal-theory approximations to exact Bayesian inference, conditional on the observed simulations. The methods are illustrated on a random-effects mixture model applied to experimental measurements of reaction times of normal and schizophrenic patients.

Shown for reading. Its publisher allows quoting it, not republishing it.

Cited by papers we hold 4

• Southern Pines Are Resistant to Mortality From an Exceptional Drought in East Texas · 2020
  Not checked
• Bird communities in sun and shade coffee farms in Kenya · 2015
  Not checked
• Spatial analysis of distribution of dengue cases in Espírito Santo, Brazil, in 2010: use of Bayesian model · 2014
  Not checked
• The mate recognition protein gene mediates reproductive isolation and speciation in the <it>Brachionus plicatilis</it> cryptic species complex · 2012
  Not checked

Reads

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.