Model-Based Clustering of Multiple Time Series
Authors: Frühwirth-Schnatter, Sylvia1; Kaufmann, Sylvia2
Source: Journal of Business & Economic Statistics, Volume 26, Number 1, January 2008 , pp. 78-89(12)
Publisher: American Statistical Association
- Free Content
- New Content
- Subscribed Content
- Free Trial Content
Abstract:
We propose to pool multiple time series into several groups using finite-mixture models. Within each group, the same econometric model holds. We estimate the groups of time series simultaneously with the group-specific model parameters using Bayesian Markov chain Monte Carlo simulation methods. We discuss model identification and base model selection on marginal likelihoods. With a simulation study, we document the efficiency gains in estimation and forecasting realized relative to overall pooling of the time series. To illustrate the usefulness of the method, we analyze extensions to unobserved heterogeneity and to Markov switching within clusters.Keywords: BUSINESS CYCLE ANALYSIS; GROWTH CONVERGENCE; MARKOV CHAIN MONTE CARLO; MARKOV SWITCHING; MIXTURE MODELING; PANEL DATA
Document Type: Research article
DOI: 10.1198/073500107000000106
Affiliations: 1: Department of Applied Statistics and Econometrics, Johannes Kepler University, Linz, Austria 2: Economic Studies Division, Oesterreichische Nationalbank, Vienna, Austria
- Free Content
- New Content
- Subscribed Content
- Free Trial Content
Click here for Page Help