Evaluating Information in Ill-Structured Decision EnvironmentsConrath, D. W.; Montazemi, A. R.; Higgins, C. A.
doi: 10.1057/jors.1987.66pmid: N/A
AbstractThe issue of evaluating information in an ill-structured decision environment is examined by comparing four alternative methods. Two are derived from the cognitive maps of the decision-makers: one is based on the intrinsic variety of the factor being evaluated, and the other on the number of links in the cognitive map that are affected by the factor's removal. The other two involve Likert scale and rank-ordering questions to measure the value of the factor directly. The four methods were tested using 10 district claim managers of an insurance company. The task involved evaluating the performance of their subordinates. The results were inconclusive, as no one measure clearly dominated the others. However, analyses of post-experiment interviews suggest that the decision-makers' evaluation of the information content of the relevant factors was inversely related to the ease with which they could infer the state (value) of a factor.
Medicinal Inventory Control in a University Health CentreŞatir, Ahmet; Cengiz, Dilek
doi: 10.1057/jors.1987.67pmid: N/A
AbstractThis paper presents a stochastic, periodic-review model used to control the medicine inventories in a university health centre. Features and formulation of the model are discussed in terms of the stockout objective and the budgetary constraint. Demand and cost data used for the three medicine groups are provided. Findings of the study are analysed within the framework of sensitivity analysis, where the expected shortage levels for the medicine groups studied are taken as the performance criteria.
Relative Efficiency Assessments Using Data Envelopment Analysis: An Application to Data on Rates DepartmentsThanassoulis, E.; Dyson, R. G.; Foster, M. J.
doi: 10.1057/jors.1987.68pmid: N/A
AbstractThis paper examines the nature of information obtained from data envelopment analysis (DEA) in comparative studies of the efficiency of decision-making units, and it discusses the interpretation and practical usefulness of such information. The themes developed in the paper are illustrated by an application of DEA to data on the rate-collection function of London Boroughs and Metropolitan District Councils. The paper begins with an overview of DEA, followed by a discussion of some of the practical considerations arising in the application of DEA. It then describes the structuring of the rate-collection function for assessment by DEA, and explores the extent to which units can be classified as relatively efficient or inefficient. In respect of relatively inefficient units, it illustrates the construction of target inputs and outputs so that their relative efficiency may improve. In respect of relatively efficient units, it is argued that their identification is weak in the sense that for some of them their apparent efficiency may be simply a reflection of an uncommon input-output profile. It is shown, nevertheless, that information about relatively efficient units can be used to identify those of them which may prove examples of good operating practice in given aspects of their function. (Readers not familiar with British taxes may wish to note that rates are a tax on property, levied by local authorities.)
Two-Dimensional Finite Bin-Packing AlgorithmsBerkey, J. O.; Wang, P. Y.
doi: 10.1057/jors.1987.70pmid: N/A
AbstractGiven a set of rectangular pieces, the two-dimensional bin-packing problem is to place the pieces into an open-ended bin of infinite height such that the height of the resulting packing is minimized. In this paper we analyse the performance of two-dimensional bin-packing heuristics when applied to the special case of packing into finite bins. We develop new bin-packing heuristics by adapting the bottom-left packing method and the next-fit, first-fit and best-fit level-oriented packing heuristics to the finite-bin case. We present our implementation of these algorithms, and compare them to other finite-bin heuristics. Our computational results indicate that the heuristics presented in this paper are suitable for practical use, and behave in a manner which reflects the proven worst-case bounds for the two-dimensional open-ended bin-packing problem.
Antithetic Bias Reduction for Discrete-Event SimulationsDeligönül, Z. Şeyda
doi: 10.1057/jors.1987.71pmid: N/A
AbstractThis study presents a technique for reducing the bias induced by arbitrary initial conditions in some discrete simulation studies. The technique relies on compensating the existing bias in a run by purposely introducing a deviation in the counter-direction during the subsequent run. Specifically, after obtaining a sample with initial condition X0, an antithetic companion run is generated starting from (2X̄ - X0). This introduces an adjustment equal and opposite to the indicated deviation, as measured by the distance between the current sample mean X̄ and the initial condition X0. Then the overall mean has a significantly lower bias. Application of the technique to first-order autoregressive process and to a machine-repair system revealed that it is capable of reducing, and in most cases practically removing, the transient effects within moderate sample sizes.
A Partially Observable Markov Decision Process with Lagged InformationKim, Soung Hie; Jeong, Byung Ho
doi: 10.1057/jors.1987.72pmid: N/A
AbstractIn actuality, we face lots of uncertainty in the application of a Markov process. In order to reduce such uncertainty, it is indispensable to use additional information concerning the state of the process.Among various kinds of additional information, this paper focuses on how to use uncertain delayed observation in a partially observable Markovian decision process (POMDP). This study develops a basic information structure, adding lagged observations to a general POMDP, and derives a rule for updating the state vector based on the information structure. This POMDP model is solved on the basis of a modified one-pass algorithm. An example is also given.
Forecasting and Inventory Control for Sporadic Demand Under Periodic ReviewSchultz, Carl R.
doi: 10.1057/jors.1987.74pmid: N/A
AbstractA sporadic or lumpy demand pattern is characterized by large transactions separated by periods of zero demand. Such demand patterns occur frequently for items in parts and supplies inventory systems. A forecasting procedure is presented, to be used in conjunction with a base-stock (order-up-to) inventory-control policy under periodic review. The procedure determines the size and timing of replenishment orders. Although a base-stock policy calls for a replenishment order after each transaction, it is shown that a delay in placing the order can result in significant holding-cost reductions with little additional risk or cost of stockouts.