The Forecasting Method Selection Tree is a convenient and effective tool that helps forecasters to use evidence-based forecasting principles to select the best methods for their problems. We have made some important changes to the Selection Tree to bring it up-to-date with current knowledge.

The changes include, first, reclassifying Delphi as a method that can be appropriate for eliciting experts' judgmental forecasts when large changes are expected; second, eliminating game theory and data mining as methods that have not been shown to produce valid forecasts; and, third, completely reworking the section of the Tree that relates to causal methods to include more conditions and, most importantly, the versatile Index method.

We found that visitors were having problems with the sticky pop-up boxes that provide detail on the conditions and methods and so we have switched this feature off for the time being. We are revising the pop-up boxes to fit with the changes we have made to the Tree and when we have done this we will re-implement the pop-ups as a simple roll-over feature.

Finally we are changing the Methodology Tree to reflect the changes we have made to the Selection Tree. Pop-ups are also turned off on the Methodology Tree while we work on the changes.

Deadline extended to 6 March 2009 for submitting abstracts for the 29th International Symposium on Forecasting in Kowloon, Hong Kong, more…

The International Institute of Forecasters Announces SAS® Grants to Support Research on Forecasting for Year 2010 (3 March, 2010)

The International Institute of Forecasters, in collaboration with SAS®, is proud to announce a grant of financial support for research on how to improve the state of the art in forecasting methods and business forecasting applications. Over twenty years of forecasting research has seen major changes in the theoretical ideas underpinning forecasting effectiveness. However, there has been less impact on forecasting methods and applications.

This will be the eighth year, after the award of grants in 2003 through 2009, in which the IIF has partnered with SAS® to offer this generous support. The grant consists of two, $5,000 awards.

Applications should be submitted to the IIF Office by 30th September 2010. For more information on this grant and how to apply, visit the IIF website Grants and Research Awards page.

 

“Enhancing group-based judgmental forecasting: processes and priorities”


In many situations, pure model-based statistical forecasting methods are impractical because of the absence of appropriate historical data, and so some form of judgmental assessment is necessary. However, individuals (including experts) frequently differ in their judgments, and so some form of judgment combination, or disagreement resolution, is essential. Should the process of combination be structured in some way – if so, how? Evidence shows that structured methods, such as Delphi, can outperform both standard interacting groups and statistical groups – where either equal or unequal weights are given to the constituent individual opinions. But what is it about, for example, the Delphi process that makes it work? This Special Issue is focused on understanding (i) judgment change and (ii) improvements in forecasting quality, within a group-based context. Potential topics include:

If you are interested in contributing to this special issue, please submit a one-page abstract to both editors of the special issue for an initial assessment. A quick response will be given regarding the suitability of the paper for the special issue. The deadline for submission of full papers is 1 June 2009 and we are aiming for the special issue to be published by summer 2010. All papers submitted will go through a double blind review process and only those papers that meet the requirements of the International Journal of Forecasting would be accepted for publication.

Please submit your initial abstract electronically to both editors listed below:

This email address is being protected from spambots. You need JavaScript enabled to view it.
Durham Business School

This email address is being protected from spambots. You need JavaScript enabled to view it.
Institute of Food Research

Over a period of little more than ten years, the ForPrin.com site has had 1,000,000 visits. The rate of visits has picked up with nearly 300,000 over the last 12 months. In addition, associated sites theclimatebet.com received more than 60,000 visits since June 2007 and PollyVote.com received more than 70,000 visits since June of this year. We expect to have achieved a total of 2 million visits to the main site by no later than December 2011 as we continue to add content and features, and improve usability.