Dynamic Predictive Density Combinations for Large Data Sets in Economics and Finance

Tinbergen Institute Discussion Paper 15-084/III

73 Pages Posted: 21 Jul 2015 Last revised: 6 Mar 2017

See all articles by Roberto Casarin

Roberto Casarin

University Ca' Foscari of Venice - Department of Economics

Stefano Grassi

University of Kent - Canterbury Campus

Francesco Ravazzolo

Free University of Bozen-Bolzano - Faculty of Economics and Management; BI Norwegian Business School

H. K. van Dijk

Tinbergen Institute; Econometric Institute

Multiple version iconThere are 2 versions of this paper

Date Written: March 10, 2016

Abstract

A Bayesian semi-parametric dynamic model combination is proposed in order to deal with a large set of predictive densities. It extends the mixture of experts and the smoothly mixing regression models by allowing combination weight dependence between models as well as over time. It introduces an information reduction step by using a clustering mechanism that allocates the large set of predictive densities into a smaller number of mutually exclusive subsets. The complexity of the approach is further reduced by making use of the class-preserving property of the logistic-normal distribution that is specified in the compositional dynamic factor model for the weight dynamics with latent factors defined on a reduced dimension simplex. The whole model is represented as a nonlinear state space model that allows groups of predictive models with corresponding combination weights to be updated with parallel clustering and sequential Monte Carlo filters. The approach is applied to predict Standard & Poor’s 500 index using more than 7000 predictive densities based on US individual stocks and finds substantial forecast and economic gains. Similar forecast gains are obtained in point and density forecasting of US real GDP, Inflation, Treasury Bill yield and employment using a large data set.

Keywords: Density Combination, Large Set of Predictive Densities, Compositional Factor Models, Nonlinear State Space, Bayesian Inference, GPU Computing

JEL Classification: C11, C15, C53, E37

Suggested Citation

Casarin, Roberto and Grassi, Stefano and Ravazzolo, Francesco and van Dijk, Herman K., Dynamic Predictive Density Combinations for Large Data Sets in Economics and Finance (March 10, 2016). Tinbergen Institute Discussion Paper 15-084/III, Available at SSRN: https://ssrn.com/abstract=2633388 or http://dx.doi.org/10.2139/ssrn.2633388

Roberto Casarin (Contact Author)

University Ca' Foscari of Venice - Department of Economics ( email )

San Giobbe 873/b
Venice, 30121
Italy
+39 030.298.91.49 (Phone)
+39 030.298.88.37 (Fax)

HOME PAGE: http://sites.google.com/view/robertocasarin

Stefano Grassi

University of Kent - Canterbury Campus ( email )

Keynes College
Canterbury, Kent CT2 7NP
United Kingdom

Francesco Ravazzolo

Free University of Bozen-Bolzano - Faculty of Economics and Management ( email )

Via Sernesi 1
39100 Bozen-Bolzano (BZ), Bozen 39100
Italy

BI Norwegian Business School ( email )

Nydalsveien 37
Oslo, 0442
Norway

HOME PAGE: http://www.francescoravazzolo.com/

Herman K. Van Dijk

Tinbergen Institute ( email )

Gustav Mahlerplein 117
Burg. Oudlaan 50
Amsterdam/Rotterdam, 1082 MS
Netherlands
+31104088955 (Phone)
+31104089031 (Fax)

HOME PAGE: http://people.few.eur.nl/hkvandijk/

Econometric Institute ( email )

P.O. Box 1738
3000 DR Rotterdam
Netherlands
+31 10 4088955 (Phone)
+31 10 4527746 (Fax)

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
229
Abstract Views
2,175
Rank
208,715
PlumX Metrics