:::
Home
Sitemap
SSL-VPN
Chinese
Webmail
Mobile
Search:
About IEAS
About IEAS
Organization
Advisory Committee
Research Fields
Research Groups and Projects
List of Directors
Introduction
News
NewsLetter
News
Research Highlights
Album
Research
Seminars
Conferences
Lectures
Recent Publications
Chung-Hua Series of Lectures
Working Papers
Books
Policy Research
Public Policy Analysis
Public Policy Workshop
People
Research Fellows
Joint Research Fellows
Adjunct Research Fellows
Corresponding Research Fellows
Postdoctoral Fellows
Visiting Scholars
Long-Term Visiting Scholars
Economic Forecast
Taiwan Economic Forecast
Historical Forecast Data
Journals
Academia Economic Papers
Introduction
Editorial Committee
Instructions to Contributors
Instructions to Contributors
Preparation of Manuscripts for AEP
Publication Ethics and Malpractice Statement
Research Papers Review System for AEP
Online Submission/Review
Call for Papers for Special Issue
Volumes and Issues
Articles in Press
Subscription Information
Contact Us
Taiwan Economic Forecast and Policy
About TEFP
Editorial Committee
Instructions for Authors
Instructions for Authors
Preparation of Manuscripts for TEFP
Publication Ethics and Malpractice Statement
Research Papers Review System for TEFP
Volumes and Issues
Call for Paper
Submit/ Review Online
Contact Us
Library
Inside Area
:::
News
Show all
Hide all
NewsLetter
News
Research Highlights
Album
:::
Location
Home
News
Research Highlights
Optimal Multi-step VAR Forecast Averaging (with Jen-Che Liao, published in ECONOMETRIC THEORY)
Previous Page
|
Print
|
Mail to Friend
Font size:
If click icon doesn't change the font size, You can also hold down
and type "+" or "-" to change the font size
Small
Medium
Large
| Share to:
Share to Twitter
Share to Plurk
Share to Facebook
Share to Google Plus
Research Highlights
Optimal Multi-step VAR Forecast Averaging (with Jen-Che Liao, published in ECONOMETRIC THEORY)
2020-12-29
Author
Jen-Che Liao
Wen-Jen Tsay
Abstract
This paper proposes frequentist multiple-equation least squares averaging approaches for multi-step forecasting with vector autoregressive (VAR) models. The proposed VAR forecast averaging methods are based on the multivariate Mallows model averaging (MMMA) and multivariate leave-h-out cross-validation averaging (MCVAh) criteria (with h denoting the forecast horizon), which are valid for iterative and direct multi-step forecast averaging, respectively. Under the framework of stationary VAR processes of in finite order, we provide theoretical justifications by establishing asymptotic unbiasedness and asymptotic optimality of the proposed forecast averaging approaches. Specifically, MMMA exhibits asymptotic optimality for one-step-ahead forecast averaging, whereas for direct multi-step forecast averaging, the asymptotically optimal combination weights are determined separately for each forecast horizon based on the MCVAh procedure. To present our methodology, we investigate the finite-sample behavior of the proposed averaging procedures under model misspecification via simulation experiments.
Link
https://www.cambridge.org/core/journals/econometric-theory/article/optimal-multistep-var-forecast-averaging/7E47C08E9ED3CC1AA329AD9CA5638045(Open New Window)
TOP