Monitoring and Improving Markov Chain Monte Carlo Convergence by Partitioning

dc.contributor.advisor

Schmidler, Scott C

dc.contributor.author

VanDerwerken, Douglas

dc.date.accessioned

2015-05-12T20:45:08Z

dc.date.available

2015-05-12T20:45:08Z

dc.date.issued

2015

dc.department

Statistical Science

dc.description.abstract

Since Bayes' Theorem was first published in 1762, many have argued for the Bayesian paradigm on purely philosophical grounds. For much of this time, however, practical implementation of Bayesian methods was limited to a relatively small class of "conjugate" or otherwise computationally tractable problems. With the development of Markov chain Monte Carlo (MCMC) and improvements in computers over the last few decades, the number of problems amenable to Bayesian analysis has increased dramatically. The ensuing spread of Bayesian modeling has led to new computational challenges as models become more complex and higher-dimensional, and both parameter sets and data sets become orders of magnitude larger. This dissertation introduces methodological improvements to deal with these challenges. These include methods for enhanced convergence assessment, for parallelization of MCMC, for estimation of the convergence rate, and for estimation of normalizing constants. A recurring theme across these methods is the utilization of one or more chain-dependent partitions of the state space.

dc.identifier.uri

https://hdl.handle.net/10161/9876

dc.subject

Statistics

dc.subject

Bayesian statistics

dc.subject

Convergence diagnostics

dc.subject

Markov chain Monte Carlo

dc.subject

Parallel MCMC

dc.title

Monitoring and Improving Markov Chain Monte Carlo Convergence by Partitioning

dc.type

Dissertation

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
VanDerwerken_duke_0066D_12820.pdf
Size:
1.17 MB
Format:
Adobe Portable Document Format

Collections