Variable Selection and Inference for Multi-Period Forecasting Problems

40 Pages Posted: 11 Feb 2009

See all articles by M. Hashem Pesaran

M. Hashem Pesaran

University of Southern California - Department of Economics; University of Cambridge - Trinity College (Cambridge)

Andreas Pick

Erasmus University Rotterdam (EUR) - Department of Econometrics; De Nederlandsche Bank

Allan Timmermann

UCSD ; Centre for Economic Policy Research (CEPR)

Multiple version iconThere are 2 versions of this paper

Date Written: February 1, 2009

Abstract

This paper conducts a broad-based comparison of iterated and direct multi-step forecasting approaches applied to both univariate and multivariate models. Theoretical results and Monte Carlo simulations suggest that iterated forecasts dominate direct forecasts when estimation error is a first-order concern, i.e. in small samples and for long forecast horizons. Conversely, direct forecasts may dominate in the presence of dynamic model misspecification. Empirical analysis of the set of 170 variables studied by Marcellino, Stock and Watson (2006) shows that multivariate information, introduced through a parsimonious factor-augmented vector autoregression approach, improves forecasting performance for many variables, particularly at short horizons.

Suggested Citation

Pesaran, M. Hashem and Pick, Andreas and Timmermann, Allan, Variable Selection and Inference for Multi-Period Forecasting Problems (February 1, 2009). CESifo Working Paper Series No. 2543, Available at SSRN: https://ssrn.com/abstract=1340396

M. Hashem Pesaran (Contact Author)

University of Southern California - Department of Economics ( email )

3620 South Vermont Ave. Kaprielian (KAP) Hall 300
Los Angeles, CA 90089
United States

University of Cambridge - Trinity College (Cambridge) ( email )

United Kingdom

Andreas Pick

Erasmus University Rotterdam (EUR) - Department of Econometrics ( email )

P.O. Box 1738
3000 DR Rotterdam
Netherlands

De Nederlandsche Bank ( email )

PO Box 98
1000 AB Amsterdam
Amsterdam, 1000 AB
Netherlands

Allan Timmermann

UCSD ( email )

9500 Gilman Drive
La Jolla, CA 92093-0553
United States
858-534-0894 (Phone)

HOME PAGE: http://rady.ucsd.edu/people/faculty/timmermann/

Centre for Economic Policy Research (CEPR)

London
United Kingdom

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

Paper statistics

Downloads
74
Abstract Views
1,118
rank
381,231
PlumX Metrics