Stochastic Benchmarking

This book introduces readers to benchmarking techniques in the stochastic environment, primarily stochastic data envelopment analysis (DEA), and provides stochastic models in DEA for the possibility of variations in inputs and outputs. It focuses on the application of theories and interpretations of the mathematical programs, which are combined with economic and organizational thinking. The book’s main purpose is to shed light on the advantages of the different methods in deterministic and stochastic environments and thoroughly prepare readers to properly use these methods in various cases. Simple examples, along with graphical illustrations and real-world applications in industry, are provided for a better understanding. The models introduced here can be easily used in both theoretical and real-world evaluations. This book is intended for graduate and PhD students, advanced consultants, and practitioners with an interest in quantitative performance evaluation.

This book covers recent advances in efficiency evaluations, most notably Data Envelopment Analysis (DEA) and Stochastic Frontier Analysis (SFA) methods. It introduces the underlying theories, shows how to make the relevant calculations and discusses applications. The aim is to make the reader aware of the pros and cons of the different methods and to show how to use these methods in both standard and non-standard cases. Several software packages have been developed to solve some of the most common DEA and SFA models. This book relies on R, a free, open source software environment for statistical computing and graphics. This enables the reader to solve not only standard problems, but also many other problem variants. Using R, one can focus on understanding the context and developing a good model. One is not restricted to predefined model variants and to a one-size-fits-all approach. To facilitate the use of R, the authors have developed an R package called Benchmarking, which implements the main methods within both DEA and SFA. The book uses mathematical formulations of models and assumptions, but it de-emphasizes the formal proofs - in part by placing them in appendices -- or by referring to the original sources. Moreover, the book emphasizes the usage of the theories and the interpretations of the mathematical formulations. It includes a series of small examples, graphical illustrations, simple extensions and questions to think about. Also, it combines the formal models with less formal economic and organizational thinking. Last but not least it discusses some larger applications with significant practical impacts, including the design of benchmarking-based regulations of energy companies in different European countries, and the development of merger control programs for competition authorities.

This book constitutes the refereed proceedings of the Third European Performance Engineering Workshop, EPEW 2006, held in Budapest, Hungary in June 2006. The 16 revised full papers presented were carefully reviewed and selected from 40 submissions. The papers are organized in topical sections on stochastic process algebra, workloads and benchmarks, theory of stochastic processes, formal dependability and performance evaluation, as well as queues, theory and practice.

"In this book, Peter Bogetoft - THE expert on the theory and practice of benchmarking - provides an in–depth yet very accessible and readable explanation of the best way to do benchmarking, starting from the ground up." Rick Antle William S. Beinecke Professor of Accounting, Yale School of Management CFO, Compensation Valuation, Inc. "I highly recommend this well-written and comprehensive book on measuring and managing performance. Dr. Bogetoft summarizes the fundamental mathematical concepts in an elegant, intuitive, and understandable way." Jon A. Chilingerian Professor, Brandeis University and INSEAD "Bogetoft gives in his book Performance Benchmarking an excellent introduction to the methodological basis of benchmarking." Christian Parbøl Director, DONG Energy "This book is the primer on benchmarking for performance management." Albert Birck Business Performance Manager, Maersk Oil "This excellent book provides a non technical introduction for performance management." Misja Mikkers, Director, Dutch Health Care Authority "With this very well written and comprehensive introduction to the many facets of benchmarking in hand, organizations have no excuse for not applying the best and cost effective benchmarking methods in their performance assessments." Stig P. Christensen Senior R&D Director, COWI

Because of the generally high computational costs that come with large-scale problems, more so on real world problems, the use of benchmarks is a common practice in algorithm design, algorithm tuning or algorithm choice/evaluation. The question is then the forms in which these real-world problems come. Answering this question is generally hard due to the variety of these problems and the tediousness of describing each of them. Instead, one can investigate the commonly encountered difficulties when solving continuous optimization problems. Once the difficulties identified, one can construct relevant benchmark functions that reproduce these difficulties and allow assessing the ability of algorithms to solve them. In the case of large-scale benchmarking, it would be natural and convenient to build on the work that was already done on smaller dimensions, and be able to extend it to larger ones. When doing so, we must take into account the added constraints that come with a large-scale scenario. We need to be able to reproduce, as much as possible, the effects and properties of any part of the benchmark that needs to be replaced or adapted for large-scales. This is done in order for the new benchmarks to remain relevant. It is common to classify the problems, and thus the benchmarks, according to the difficulties they present and properties they possess. It is true that in a black-box scenario, such information (difficulties, properties...) is supposed unknown to the algorithm. However, in a benchmarking setting, this classification becomes important and allows to better identify and understand the shortcomings of a method, and thus make it easier to improve it or alternatively to switch to a more efficient one (one needs to make sure the algorithms are exploiting this knowledge when solving the problems). Thus the importance of identifying the difficulties and properties of the problems of a benchmarking suite and, in our case, preserving them. One other question that rises particularly when dealing with large-scale problems is the relevance of the decision variables. In a small dimension problem, it is common to have all variable contribute a fair amount to the fitness value of the solution or, at least, to be in a scenario where all variables need to be optimized in order to reach high quality solutions. This is however not always the case in large-scales; with the increasing number of variables, some of them become redundant or groups of variables can be replaced with smaller groups since it is then increasingly difficult to find a minimalistic representation of a problem. This minimalistic representation is sometimes not even desired, for example when it makes the resulting problem more complex and the trade-off with the increase in number of variables is not favorable, or larger numbers of variables and different representations of the same features within a same problem allow a better exploration. This encourages the design of both algorithms and benchmarks for this class of problems, especially if such algorithms can take advantage of the low effective dimensionality of the problems, or, in a complete black-box scenario, cost little to test for it (low effective dimension) and optimize assuming a small effective dimension. In this thesis, we address three questions that generally arise in stochastic continuous black-box optimization and benchmarking in high dimensions: 1. How to design cheap and yet efficient step-size adaptation mechanism for evolution strategies? 2. How to construct and generalize low effective dimension problems? 3. How to extend a low/medium dimension benchmark to large dimensions while remaining computationally reasonable, non-trivial and preserving the properties of the original problem?

A framework for financial market modeling, the benchmark approach extends beyond standard risk neutral pricing theory. It permits a unified treatment of portfolio optimization, derivative pricing, integrated risk management and insurance risk modeling. This book presents the necessary mathematical tools, followed by a thorough introduction to financial modeling under the benchmark approach, explaining various quantitative methods for the fair pricing and hedging of derivatives.

The aim of this special issue is to publish original research papers that cover recent advances in the theory and application of stochastic processes. There is especial focus on applications of stochastic processes as models of dynamic phenomena in various research areas, such as queuing theory, physics, biology, economics, medicine, reliability theory, and financial mathematics. Potential topics include, but are not limited to: Markov chains and processes; large deviations and limit theorems; random motions; stochastic biological model; reliability, availability, maintenance, inspection; queueing models; queueing network models; computational methods for stochastic models; applications to risk theory, insurance and mathematical finance.

This book addresses stochastic optimization procedures in a broad manner. The first part offers an overview of relevant optimization philosophies; the second deals with benchmark problems in depth, by applying a selection of optimization procedures. Written primarily with scientists and students from the physical and engineering sciences in mind, this book addresses a larger community of all who wish to learn about stochastic optimization techniques and how to use them.

The author presents the techniques and theory of benchmarking to explain how performance indices and rankings are developed and used to improve efficiency, productivity and profitability. The only software required is Microsoft Excel.