A simple method to compute economic order quantities: Some observations

Teng [2] presents an arithmetic–geometric mean method to be applied to determine the optimal lot size for the EOQ/EPQ models, taking into account backorders. Although the arithmetic–geometric mean method is correct, arguments as to when (not) to use the arithmetic–geometric mean inequality as optimization method are not complete. Moreover, this optimization method does not focus on the method for deriving the optimal backorders level. The main purpose of this work is to overcome these shortcomings, presents a discussion of when (not) to use the cost minimization method and derives the optimal backorders level.     

Expected cost bounds for the selection and ordering procedures based on binary-type questions

The problems considered in this paper are similar to those studied by Arrow, Pesotchinsky and Sobel (1981). We search for the optimal methods of ordering of a sample or of identifying sample order statistics by asking binary type questions and employing the criterion which defines the cost of a question as the number of responses. The asymptotic results show that our procedures with simple algorithms are comparable (in terms of cost) with the best known methods for ordering by using pairwise comparisons.     

Clusterwise aggregation of relations

In this paper we handle the general problem of finding q(> 1) central relations on a set of objects which best fit the information contained in a finite number of given relations on that set. The proposed CAR (clusterwise aggregation of relations) algorithm allows one to consider the well-known situation of determining a single central relation as a special case (q = 1) and takes into account the fact that the representation of appropriately selected subsets of relations by different central relations can provide additional insights into whether different clusters or segments of relations exist in the given set of relations. Two examples demonstrate the usefulness of the suggested approach.     

Judgement by pairwise comparisons

This article gives an alternative solution to the problem of W. Gaul and M. Schader (Vol. 4, no. 4 pp. 273–282).     

Vergleichsmessung der spezifischen Aktivität einer 90Sr/90Y-Lösung zwischen dem ASMW Berlin und dem WNIIM Leningrad

In der Arbeit wird über eine internationale Vergleichsmessung berichtet, die die beteiligten Institutionen zur Überprüfung der Genauigkeit ihrer Normalmeβeinrichtungen zur Darstellung der Aktivitätseinheit β-strahlender Nuklide durchführten. Verschiedene Korrektionsfaktoren sowie die Verfahren ihrer Ermittlung werden diskutiert. Die Abweichung der Ergebnisse beträgt 0,7% und liegt damit innerhalb der angegebenen Fehlergrenzen.     

Performance indication improvement for a proficiency testing

The paper discusses peculiarities of Z scores and E _n numbers, which are most often used for the treatment of proficiency test data. The important conditions of proper usage of these performance indicators and their improvement are suggested on the basis of systematic approach, on the idea of accuracy classification, and on some principles of optimality borrowed from information theory. The author believes that this paper may be of interest and practical value for all those engaged in applied metrology, specifically in the field of developing of and participating in proficiency testing programs, and in the activity connected with accrediting testing and calibration laboratories.Presented at 15th International Conference on Quality in Israel, November 2004     

EAL interlaboratory comparison Wa1 – Testing of potable water

 The accreditation of laboratories has emphasized the use of interlaboratory comparisons as a tool to monitor the comparability and accuracy of results laboratories produce. An interlaboratory comparison for water laboratories was organized among European Cooperation for Accreditation (EA) member countries; 30 laboratories, 7 of which were not accredited, from 14 European countries participated in this intercomparison. All the laboratories were chosen by the appropriate national accreditation bodies, with the instruction to select as participants those laboratories which act as national reference laboratories in this field. About 90% of the data collected was considered satisfactory after statistical treatment. Non-accredited laboratories performed as well as accredited laboratories. The laboratories were asked to take corrective action and report the corrections to the accreditation bodies. A great variation in the reported uncertainties of the results was observed. There seems to be a need to organize EA interlaboratory comparisons for national reference laboratories analysing water. It is obvious that even reference laboratories need training in how to estimate the uncertainty of results. Received: 22 July 1998 · Accepted: 21 September 1998     

Determination of persistent organohalogenated pollutants in human hair reference material (BCR 397): an interlaboratory study

A human powdered hair material (BCR 397) was tested for its content in persistent organic pollutants (POPs), such as polychlorinated biphenyls (PCBs), organochlorine pesticides (OCPs) and polybrominated diphenyl ethers (PBDEs). Using different methods, three laboratories (two from Canada and one from Belgium) analysed a powdered hair sample to evaluate some methodologies and to obtain consensus values for selected POPs. Measured values for all PCB congeners and p,p-DDE were within a relative standard deviation (RSD) of 15%. These first results contribute to the accuracy and precision for POPs quantification in hair and render test results more comparable among different laboratories.     

Improvements in performance in medical diagnostics tests documented by interlaboratory comparison programs

There is evidence to support the notion that interlaboratory comparisons (ILCs) are an effective tool for laboratory improvement. However, despite widespread experience and anecdotal evidence of improvements there are few published studies demonstrating any benefits from ILCs– in any field of testing. Published demonstrations of benefits can help justify the growing use of ILCs. ILCs and proficiency testing have been common for many years in medical laboratories; there has been open information on the results of ILCs, and there has been standardization of results from thousands of laboratories. These studies show general improvement over time in several areas of testing in different countries. Many articles cite specific reasons for the improvements, either proven or supposed. An early version of this paper was presented at the International Laboratory Accreditation Cooperation Conference ”ILAC 2000” in Washington D.C., on 31October, 2000. Received: 10 February 2001 Accepted: 21 January 2002