International health spending forecasts: Concepts and evaluation

Health care depends on the organizational and financial decisions which constituted each national system. Since those decisions were made at various times over the preceding years under different macroeconomic conditions, current expenditures are a distributed lag function of GDP growth and inflation rates. The accuracy of forecasts from such causal econometric models are compared to exponential smoothing, moving average, and ARIMA methods. Data for 19 OECD countries 1965-79 are used for calibration, and then ex ante forecasts are generated for 1980-87 so that actual forecast accuracy can be tested. The greatest reduction in mean absolute error was obtained with the econometric model estimated in aggregate across all 19 countries, although single-country models, exponential smoothing and international averaging were also effective. A combination of all four forecasts was more accurate than any one alone, reducing MAE by 25% relative to a constant growth projection.