Content area
Full Text
ABSTRACT
This paper analyses the size and nature of the errors in GDP forecasts in the G7 countries from 1971 to 1995. These GDP short-term forecasts are produced by the Organization for Economic Cooperation and Development and by the International Monetary Fund, and published twice a year in the Economic Outlook and in the World Economic Outlook, respectively. The evaluation of the accuracy of the forecasts is based on the properties of the difference between the realization and the forecast. A forecast is considered to be accurate if it is unbiased and efficient. A forecast is unbiased if its average deviation from the outcome is zero, and it is efficient if it reflects all the information that is available at the time the forecast is made. Finally, we also examine tests of directional accuracy and offer a non-parametric method of assessment. Copyright (C) 2000 John Wiley & Sons, Ltd.
KEY WORDS forecast evaluation; macroeconomic forecast
INTRODUCTION
Over the last few years many national and international organizations have produced reports aimed at analysing the economic situation and at providing forecasts for the future evolution of the main macroeconomic (R)gures. The purpose of this paper is to examine the size and nature of the errors in GDP forecasts in the G7 countries from 1971 to 1995. These GDP short-term forecasts are produced by the Organization for Economic Cooperation and Development (OECD) and by the International Monetary Fund (IMF), and published twice a year in the Economic Outlook and in the World Economic Outlook, respectively.
An analysis of the economic forecasts produced by the OECD, the IMF and by other organizations reveals that: (1) the forecasts made by economists linked to different organizations and institutions tend to be suspiciously similar; (2) these forecasts are usually incorrect, that is, substantial differences arise between the forecasts and the (R)nal economic growth; (3) there is a generalized belief that the events which occur in the present will be repeated in the future (the economists are `momentum-followers' who believe today's events will reoccur tomorrow); and (4) the economic forecasts tend to be very conservative, avoiding taking risks when it comes to making diagnoses on the future evolution of an economy. To address these points, this article performs an evaluation of the...