Estimating Demand Uncertainty Using Judgmental Forecasts

Measuring demand uncertainty is a key activity in supply chain planning. Of various methods of estimating the standard deviation of demand, one that has been employed successfully in the recent literature uses dispersion among experts’ forecasts. However, there has been limited empirical validation of this methodology. In this paper we provide a general methodology for estimating the standard deviation of a random variable using dispersion among experts’ forecasts. We test this methodology using three datasets, demand data at item level, sales data at firm level for retailers, and sales data at firm level for manufacturers. We show that the standard deviation of a random variable (demand and sales for our datasets) is positively correlated with dispersion among experts’ forecasts. Further we use longitudinal datasets with sales forecasts made 3-9 months before earnings report date for retailers and manufacturers to show that the effects of dispersion and scale on standard deviation of forecast error are consistent over time. * The authors gratefully acknowledge James Zeitler, Research Database Analyst at Harvard Business School for help in obtaining and preparing the data for this study. † Leonard N. Stern School of Business, New York University, 44 West 4-th St., New York, NY 10012, Ph: 212-998-0297, Fax: 212-995-4227. E-mail: [email protected]. ‡ Harvard Business School, T-81C, Morgan Hall, Soldiers Field, Boston, MA 02163, Ph: 617 496-9890, Fax: 617 496-4059, E-mail: [email protected]. § Harvard Business School, T-11, Morgan Hall, Soldiers Field, Boston, MA 02163, Ph: 617 495-6937, Fax: 617 496-4059, E-mail: [email protected]. ** The Wharton School, University of Pennsylvania, Jon M. Huntsman Hall, 3730 Walnut St., Philadelphia, PA 19104-6366, Ph: 215 898-7721, Fax: 215 898-3664, E-mail: [email protected].