Fall 2007 Issue

Special Feature: Delphi and Prediction Markets

  • A Guide to Delphi by Gene Rowe
    When we rely on the judgment of experts to help produce our forecasts, the key issues are how to get the appropriate information out of our experts and how to get a forecast if we are using multiple experts. Gene Rowe describes the Delphi method, what it offers to the forecaster, and what the pitfalls are in its implementation.
  • Methods To Elicit Forecasts From Groups Delphi And Prediction Markets Compared by Kesten Green, J. Scott Armstrong, and Andreas Graefe
    The Delphi technique is better than traditional group meetings for forecasting and has some advantages over another promising alternative to meetings, prediction markets. In this article, Kesten, Scott, and Andreas observe the increasing popularity of Delphi, describe the benefits of using this method to obtain forecasts from experts, compare it with prediction markets, and conclude that Delphi should be used more widely.


    1. Good And Bad Judgment In Forecasting Lessons From Four Companies by Robert Fildes and Paul Goodwin
      In their ongoing investigation into corporate forecasting practices, Robert Fildes and Paul Goodwin have uncovered evidence of excessive use of judgmental adjustment to statistical forecasts. In this report, they document the extent of the problem within four large companies, explore the motivations that lead business forecasters to this sometimes counter-productive behavior, and offer a series of recommendations to ensure that forecast adjustments are made for the right reasons.
    2. How to Project Patient Persistency by Ka Lok Lee, Peter Fader, and Bruce Hardie
      Pharmaceutical companies face the problem of how to project the persistency patterns of patients who are taking their manufactured medications – i.e., how to determine the percentage of patients who will continue to refill a given prescription on a timely basis. The authors have developed a probability model with a well-grounded story for the dropout process. The model, which can be implemented in a simple Excel spreadsheet, provides remarkably accurate forecasts as well as other useful diagnostics about patient persistency.
    3. The Keys to the White House Forecast for 2008 by Allan J. Lichtman
      The Keys to the White House is a historically based model that has forecast well ahead of time the winners of every presidential election from 1984 through 2004. The theory behind the Keys is that presidential election results turn primarily on the performance of the party controlling the White House, and that politics-as-usual by the challenging candidate will have no impact on results. In this update of his earlier Keys article in Foresight, Allan Lichtman discusses why the Keys model predicts a Democratic Party takeover of the White House in 2008.
    4. Bayesian Forecasting Methods For Short Time Series by Enrique De Alba And Manuel Mendoza
      This article by Enrique de Alba and Manuel Mendoza extends Foresight’s previous coverage of methods for forecasting seasonal data when the historical series is short (less than 2-3 years of data). The authors describe and illustrate a Bayesian method for seasonal data and show that it can outperform traditional time series methods for short time series.

Additional information


Complete Issue, Special Feature, Special Feature 1, Special Feature 2, Article 1, Article 2, Article 3, Article 4, Article 5, Article 6, Article 7, Article 8, Article 9, Free Article, Free Article 1, Free Article 2, Free Article 3