Title of Paper Annual Energy Outlook Forecast Evaluation

by 
Susan H. Holte

OIAF has been providing an evaluation of the forecasts in the Annual Energy Outlook (AEO) annually since 1996. Each year, the forecast evaluation expands on that of the prior year by adding the most recent AEO and the most recent historical year of data. However, the underlying reasons for deviations between the projections and realized history tend to be the same from one evaluation to the next. The most significant conclusions are:

Because the underlying reasons for differences between the projections and realized history do not generally change from one year to the next, the text of last year's analysis was not updated this year. The 1999 forecast evaluation with the complete narrative is available at www.eia.gov/oiaf/issues/forecast.html.

The last column of Table 1 provides a summary of the average absolute forecast errors for each of the major variables included in this analysis, which are shown in more detail in Tables 2 through 18. The average absolute forecast error is computed as the mean, or average, of all the absolute values of the percentage errors, expressed as percentage differences of the reference case projection from actual, shown for each AEO, for each year in the forecast, for a given variable. Table 1 also shows the same summary of forecast errors from the four previous evaluations. As indicated in Table 1, the forecasts of consumption, carbon dioxide emissions, production, and gross domestic product have generally been the most accurate, and the forecasts of prices the least accurate. The percent errors change from one year's evaluation to the next as an additional year of data and projections is added.

Table 1. Average Absolute Percent Errors from AEO Forecast Evaluations: 1996 to 2000

For the most part, the percent errors remain similar or improve over time; however, the errors for net coal exports have increased significantly. Between 1998 and 1999, a sharp decline in coal exports coupled with a slight increase in imports resulted in a decline in net coal exports from 69 to 49 million short tons. Gross coal exports declined by 25 percent in 1999, due in part to lower world coal prices, reflecting lower mine costs at U.S. competitors, including productivity improvements in Australia, and favorable exchange rates that enabled them to lower their prices in U.S. dollars. In addition, there are increased competitive pressures on coal from natural gas in Europe. U.S. coal imports increased by 4 percent in 1999 as result of low prices for offshore coal and increased demand for low-sulfur coal to prepare for the stricter sulfur emission requirements of Phase II of the Clean Air Act Amendments of 1990.

The gross domestic product (GDP), shown in Table 17, has just undergone a change in definition by the Bureau of Economic Analysis. In the revised GDP series, computer software is now included as a component of investment, rather than an intermediate input to production. In addition, there have been statistical changes that update the national product and income accounts to reflect new and improved methodologies and newly available and revised source data. These changes are reflected in the revised set of actual values in Table 17 and cause the percent error in Table 1 to be larger in the 2000 forecast evaluation than in previous evaluations.

This year, the forecast evaluation includes carbon dioxide emissions for the first time, which are shown in Table 18. The series of carbon dioxide emissions projections begins with the Annual Energy Outlook 1993. Although carbon dioxide emissions and total energy consumption are evaluated over a different time period, the average absolute percent errors for both variables are 1.8 percent. The general pattern of errors in the carbon dioxide emissions estimates is similar to that for the energy consumption estimates. Carbon dioxide emissions and consumption were generally underestimated in the Annual Energy Outlook 1996 and earlier. Total energy consumption grew very slowly in both 1997 and 1998, resulting in more recent overestimations of both energy consumption and carbon dioxide emissions. In the case of emissions, the largest percent error is the 3-percent overestimate of 1999 emissions in the Annual Energy Outlook 1998.

 

If you would like to received any information relating to any of our reports via e-mail, click on the link labeled "Projections ListServ" to Join by entering your e-mail address.

File last modified: August 29,  2000

URL: http://www.eia.gov/oiaf/analysispaper/forecast_eval.html

Need Help Now?
Call the National Energy Information Center (NEIC)
(202) 586-8800 9AM - 5PM eastern time

  If you are having technical problems with this site,
please contact the EIA Webmaster at wmaster@eia.doe.gov