Design and Analysis of Simulation Experiments

ISBN-13: 9781441944153 / Angielski / Miękka / 2010 / 220 str.

Jack P. C. Kleijnen

Opis

Design and Analysis of Simulation Experiments (DASE) focuses on statistical methods for discrete-event simulation (such as queuing and inventory simulations). In addition, the book discusses DASE for deterministic simulation (such as engineering and physics simulations). The text presents both classic and modern statistical designs. Classic designs (e.g., fractional factorials) assume only a few factors with a few values per factor. The resulting input/output data of the simulation experiment are analyzed through low-order polynomials, which are linear regression (meta) models. Modern designs allow many more factors, possible with many values per factor. These designs include group screening (e.g., Sequential Bifurcation, SB) and space filling designs (e.g., Latin Hypercube Sampling, LHS). The data resulting from these modern designs may be analyzed through low-order polynomials for group screening and various metamodel types (e.g., Kriging) for LHS. Design and Analysis of Simulation Experiments is an authoritative textbook and reference work for researchers, graduate students, and technical practitioners in simulation. Basic knowledge of simulation and mathematical statistics are expected; however, the book does summarize these basics, for the readers' convenience. In addition, the book provides relatively simple solutions for (a) selecting problems to simulate, (b) how to analyze the resulting data from simulation, and (c) computationally challenging simulation problems.

Recenzje

"This work represents a lucid, comprehensive, authoritative, and highly informative presentation of the techniques and methodology associated with simulation experimentation. The book is 'lucid' because, as the word implies, it sheds light on the subject matter of simulation experimentation and optimization; it is 'comprehensive' because it addresses all of the essential topics in the field; it is 'authoritative'' because it captures the essence of the best research in the field, as evidenced by its more than 400 authoritative citations; and it is ''informative' in that it distills the most important scholarship of the last six decades into a 210-page study of the DASE field. Jack Kleijnen has once again produced a cutting-edge approach to the design and analysis of simulation experiments. His 1974-75 books were an incisive compilation of statistical methodology in simulation and introduced the term metamodeling to the lexicon of simulation experimentation. His 2008 volume Design and Analysis of Simulation Experiments promises to popularize the term DASE in the same way. Many of us who specialize in the field of simulation experimentation and optimization have avidly followed Kleijnen's writings for almost four decades. This latest work leads the way in this endeavor, and is a vital addition to the important scholarship in the field." (William E. BILES, JASA, June 2009, Vol. 104, No. 486)

Spis treści

Low-order polynomial regression metamodels and their designs: basics.- Classic assumptions revisited.- Simulation optimization.- Kriging metamodels.- Screening designs.- Epilogue.

O autorze

Jack Kleijnen is well known internationally for being a leading researcher in simulation for more than 30 years. He is the author of highly cited books in the area of statistical techniques in simulation that were published between 1974 and 1992. He is an excellent writer and researcher, and hence, ideally suited to write this important book for the field. 

On 25 February 2008 Her Majesty Beatrix, Queen of the Netherlands, appointed Jack Kleijnen a Knight in the Order of the Netherlands Lion.

 

Blurb

This is an advanced expository book on statistical methods for the Design and Analysis of Simulation Experiments (DASE). Though the book focuses on DASE for discrete-event simulation (such as queuing and inventory simulations), it also discusses DASE for deterministic simulation (such as engineering and physics simulations). The text presents both classic and modern statistical designs. Classic designs (e.g., fractional factorials) assume only a few factors with a few values per factor. The resulting input/output data of the simulation experiment are analyzed through low-order polynomials, which are linear regression (meta)models. Modern designs allow many more factors, possible with many values per factor. These designs include group screening (e.g., Sequential Bifurcation, SB) and space filling designs (e.g., Latin Hypercube Sampling, LHS). The data resulting from these modern designs may be analyzed through low-order polynomials for group screening and various metamodel types (e.g., Kriging) for LHS.

In this way, the book provides relatively simple solutions for the problem of which scenarios to simulate and how to analyze the resulting data.

The book also includes methods for computationally expensive simulations. It discusses only those tactical issues that are closely related to strategic issues; i.e., the text briefly discusses run-length and variance reduction techniques.

The leading textbooks on discrete-event simulation pay little attention to the strategic issues of simulation. The author has been working on strategic issues for approximately forty years, in various scientific disciples--such as operations research, management science, industrial engineering, mathematical statistics, economics, nuclear engineering, computer science, and information systems.

The intended audience is comprised of researchers, graduate students, and mature practitioners in the simulation area. They are assumed to have a basic knowledge of simulation and mathematical statistics; nevertheless, the book summarizes these basics, for the readers' convenience.