Adaptive Markov chain Monte Carlo sampling and estimation in Mata

Matthew Baker

No 440, Economics Working Paper Archive at Hunter College from Hunter College Department of Economics

Abstract: I describe algorithms for drawing from distributions using adaptive Markov chain Monte Carlo (MCMC) methods, introduce a Mata function for per- forming adaptive MCMC, amcmc(), and a suite of functions amcmc_*() allowing an implementation of adaptive MCMC using a structure. To ease use in application to estimation problems, amcmc() and amcmc_*() can be used in conjunction with models set up to work with Mata’s moptimize( ) or optimize( ), or with stand-alone functions. I apply the routines in a simple estimation problem, in drawing from a distributions without a normalizing constant, and in Bayesian estimation of a mixed logit model.

Keywords: Stata; Mata; Markov chain Monte Carlo; drawing from distributions; Bayesian estimation; mixed logit (search for similar items in EconPapers)
JEL-codes: C11 C13 C15 C18 (search for similar items in EconPapers)
Date: 2013
New Economics Papers: this item is included in nep-ore
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://econ.hunter.cuny.edu/wp-content/uploads/sit ... /HunterEconWP440.pdf (application/pdf)

Related works:
Journal Article: Adaptive Markov chain Monte Carlo sampling and estimation in Mata (2014)
Working Paper: Adaptive Markov chain Monte Carlo sampling and estimation in Mata (2014)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:htr:hcecon:440

Access Statistics for this paper

More papers in Economics Working Paper Archive at Hunter College from Hunter College Department of Economics 695 Park Avenue, New York, NY 10065. Contact information at EDIRC.
Bibliographic data for series maintained by Jonathan Conning ().