Evaluating GDP Forecasting Models for Korea
March 1, 2011
Disclaimer: This Working Paper should not be reported as representing the views of the IMF.The views expressed in this Working Paper are those of the author(s) and do not necessarily represent those of the IMF or IMF policy. Working Papers describe research in progress by the author(s) and are published to elicit comments and to further debate
Summary
This paper develops a new forecasting framework for GDP growth in Korea to complement and further enhance existing forecasting approaches. First, a range of forecast models, including indicator- and pure time-series models, are evaluated for their forecasting performance. Based on the evaluation results, a new forecasting framework is developed for GDP projections. The framework also generates a data-driven reference band for the projections, and is therefore convenient to update. The framework is applied to the current World Economic Outlook (WEO) forecast period and the Great Recession to compare its performance to past projections. Results show that the performance of the new framework often improves the forecasts, especially at quarterly frequency, and the forecasting exercise will be better informed by cross-checking with the new data-driven framework projections.
Subject: Economic forecasting, GDP forecasting, Private consumption, Time series analysis, Vector autoregression
Keywords: GDP, WP
Pages:
23
Volume:
2011
DOI:
Issue:
053
Series:
Working Paper No. 2011/053
Stock No:
WPIEA2011053
ISBN:
9781455220977
ISSN:
1018-5941






