Scott Armstrong will present findings on the accuracy of forecasts from novel but evidence-based methods for forecasting election results in a keynote speech at the International Symposium on Forecasting in Hong Kong in June. The research is part of the PollyVote Project with colleagues Alfred G. Cuzán, Andreas Graefe, and Randall Jones. We encourage you to tell us what your expectations are for the research, by filling in the questionnaire.
Please bear with us as we work through the backlog of news items that you have provided us with. We got behind on posting news during the changeover process, but it will all get posted as we iron out a few wrinkles and become familiar with the operation of the site's Joomla software. Do keep sending us news that relates to forecasting principles.
While the URL ForecastingPrinciples.com reflects the name and content of the site, we decided that it would help visitors to site if we reduced the number of characters they needed to type. We choose ForPrin.com and have incorporated this new URL into the new site logo. You will find the logo on the top left of each page; wherever you are, clicking on it will take you back to the site's welcome page.
Do judgmental adjustments of statistical forecasts of demand improve accuracy? Companies certainly believe adjustment helps: a survey by Fildes and Goodwin estimated that 34% of statistical forecasts were subsequently judgmentally adjusted. Now a large empirical study by Fildes, Goodwin, Lawrence, and Nikolopoulos (2009) has shown that on average adjustments do help, but only when something important has happened, is planned, or is expected that has not been included in the statistical model.
While management adjustments can incorporate useful information to improve forecast accuracy, they are expensive and they may introduce bias. Because the managers' adjustments in the study were made in an unstructured manner, it seems likely that further improvements in the use of managerial judgments are possible.