Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/129721 
Year of Publication: 
2015
Series/Report no.: 
Sveriges Riksbank Working Paper Series No. 307
Publisher: 
Sveriges Riksbank, Stockholm
Abstract: 
We propose a generic Markov Chain Monte Carlo (MCMC) algorithm to speed up computations for datasets with many observations. A key feature of our approach is the use of the highly efficient difference estimator from the survey sampling literature to estimate the log-likelihood accurately using only a small fraction of the data. Our algorithm improves on the O(n) complexity of regular MCMC by operating over local data clusters instead of the full sample when computing the likelihood. The likelihood estimate is used in a Pseudo- marginal framework to sample from a perturbed posterior which is within O(m-1/2) of the true posterior, where m is the subsample size. The method is applied to a logistic regression model to predict firm bankruptcy for a large data set. We document a significant speed up in comparison to the standard MCMC on the full dataset.
Subjects: 
Bayesian inference
Markov Chain Monte Carlo
Pseudo-marginal MCMC
estimated likelihood
GLM for large data
JEL: 
C11
C13
C15
C55
C83
Document Type: 
Working Paper

Files in This Item:
File
Size
709.95 kB





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.