Combining statistical and
judgmental forecasts via a web-based tourism demand forecasting system.
A manager with years of experience may tend to lean on
judgmental forecasts because of past experience.
Judgmental forecasts are often used when historical data are not available, such as a new and unique capital project.
When evaluating DSGE models on an absolute basis, however, we find that the benchmark estimated mediumscale DSGE model forecasts inflation and GDP growth very poorly, although statistical and
judgmental forecasts do equally poorly.
Researching forecasting practices 12 years ago Wisner and Stanley (1994), reported on a 1992 survey of supply chain managers that found
judgmental forecasts were favored, and that managers were not taking full advantage of the improved forecasting techniques available.
Monthly data (money supply (MI), the unemployment rate, and the Treasury bill rate) are defined to include quantities reported in two different quarters in order to avoid giving an unfair advantage to the large model with
judgmental forecasts to which Litterman's model is being compared.
However, there are differences in the emphasis given to model-based forecasts relative to
judgmental forecasts and those based on expert opinion.
Econometric and
judgmental forecasts were obtained from commercial forecasting agencies.
If the linkages among policy, the economy, and prices were well enough understood, reasonably stable over time, and mostly free from noise, they might be captured by a reliable empirical model or perhaps by
judgmental forecasts. Then the job of implementing policy might still be straightforward: Policy adjustments, though perhaps not adhering to transparent rules of thumb, could be calibrated from the model or
judgmental forecast, taking into account the inflation objectives and output constraints of the authorities.
Research suggests that
judgmental forecasts can also be improved by simply averaging the results of multiple independent forecasts.
Judgmental forecasts should be another tool as well.