The Power Approximation: Control of Multi-Item Inventory Systems with Constant Standard-Deviation-to-Mean Ratio for Demand.
Abstract
In this simulation study, the author considers the performance of the Power Approximation (Ehrhardt (1976)) for a multi-item inventory system in which the underlying demand distributions are negative binomial with constant standard-deviation-to-mean ratio of 1. The Power Approximation formulas (Ehrhardt (1976)) were obtained by least squares regression, using data from inventory items with Poisson demand distributions and negative binomial demand distributions with variance-to-mean ratios of 3 and 9. Previous experiments have all considered the effectiveness of the Approximation for systems with constant variance-to-mean ratio. The author examines the constant standard-deviation-to-mean system for the situation of full information and for the situation in which the decision-maker's knowledge is limited to a sample of previously-realized demands. In addition, the research examines the accuracy of statistical forecasts that predict the future behavior of operating characteristics. As a result, an inventory systems designer is apprised of both the costs of imperfect information and the extent of bias in the forecast estimates.
Document Details
- Document Type
- Technical Report
- Publication Date
- Nov 01, 1976
- Accession Number
- ADA034263
Entities
People
- John G. Klincewincz
Organizations
- Yale University