Estimates the Optimal Ordering Quantity in the Newsboy Problem: Bootstrap Method.

• Main Authors: Yi-Liang Chen, 陳奕良
• Other Authors: Ji-Cheng Wu
• Format: Others
• Language: zh-TW
• Published: 2008
• Online Access: http://ndltd.ncl.edu.tw/handle/33212274328600478252

碩士 === 國立屏東科技大學 === 工業管理系所 === 96 === Newsboy problem, also known as the single-period stochastic demand inventory problem, is to find the order quantity which minimizes the expected cost or maximizes the expected profit. The classical newsboy model assumes that the demand is a random variable with known distribution. Base on this assumption, the expected total cost or profit function can be constructed and the optimal order quantity can be obtained by using differential method. However, in reality failure to meet demand is always associated with a specified known distribution. Thus, the above procedure to find the optimal order quantity does not work for the classical newsboy problem. The aim of this research is to relax the assumption and to extend the analysis of the distribution-free newsboy model. The analysis is based on the collection of historical demand information and use nonparametric bootstrap method to estimate the optimal order quantity. In order to evaluate the performance of bootstrap estimate, the relative errors are computed when the demand obey exponential, normal, Poisson and negative binomial distribution, respectively. The numerical results will afford retailers to decide on the optimal order of the basis for decision-making.