For many years various types of forecast models have reportedly been used in hospital foodservice systems to estimate the patient census level or meal demand for menu items. None of these reports have dealt with the application of forecast models in a hospital cafeteria setting. The purpose of this study was to test selected forecast models in a hospital setting to determine the one that most accurately predicted the number of customers utilizing the cafeteria on a particular day, and the number of servings of a specific food item that was utilized at selected meals. Historical data was used to fit three Forecast models—Simple Moving Average, Exponential Smoothing and Adaptive Exponential Smoothing—for actual use. When results of these models were evaluated, an Analysis of Variance test showed no significant difference between forecasting accuracy. Because it is a less complex model to use. Simple Moving Average was chosen to forecast for actual entrée demand. Graphing forecasts from Simple Moving Average against actual demand resulted in very similar curves indicating that managers, with no forecasting system or a system having a high degree of error, might benefit from the use of any of the models evaluated.
Bertrum C. Connell
Kenneth I. Burke
Master of Science (MS)
Year Degree Awarded
Date (Title Page)
Library of Congress/MESH Subject Headings
Food Service; Hospital
Loma Linda University Libraries
This title appears here courtesy of the author, who has granted Loma Linda University a limited, non-exclusive right to make this publication available to the public. The author retains all other copyrights.
Davis, M. Sue, "Customer and Food Item Selection Forecasting in a Hospital Cafeteria" (1985). Loma Linda University Electronic Theses, Dissertations & Projects. 1258.
Loma Linda University Electronic Theses and Dissertations
Loma Linda University. Del E. Webb Memorial Library. University Archives