Particle Learning for Fat-Tailed Distributions

Hedibert F. Lopes and Nicholas G. Polson

Econometric Reviews, 2016, vol. 35, issue 8-10, 1666-1691

Abstract: It is well known that parameter estimates and forecasts are sensitive to assumptions about the tail behavior of the error distribution. In this article, we develop an approach to sequential inference that also simultaneously estimates the tail of the accompanying error distribution. Our simulation-based approach models errors with a t ν -distribution and, as new data arrives, we sequentially compute the marginal posterior distribution of the tail thickness. Our method naturally incorporates fat-tailed error distributions and can be extended to other data features such as stochastic volatility. We show that the sequential Bayes factor provides an optimal test of fat-tails versus normality. We provide an empirical and theoretical analysis of the rate of learning of tail thickness under a default Jeffreys prior. We illustrate our sequential methodology on the British pound/U.S. dollar daily exchange rate data and on data from the 2008--2009 credit crisis using daily S&P500 returns. Our method naturally extends to multivariate and dynamic panel data.

Date: 2016
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1080/07474938.2015.1092809 (text/html)
Access to full text is restricted to subscribers.

Related works:
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:taf:emetrv:v:35:y:2016:i:8-10:p:1666-1691

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/LECR20

DOI: 10.1080/07474938.2015.1092809

Access Statistics for this article

Econometric Reviews is currently edited by Dr. Essie Maasoumi

More articles in Econometric Reviews from Taylor & Francis Journals
Bibliographic data for series maintained by ().