tailieunhanh - Motivated Metamodels

In this study we explore some of the issues in depth for a particular example. We then suggest ways to improve the quality of metamodeling by striking a synthesis between statistical and more phenomenological approaches. | Project AIR FORCE Motivated Metamodels Synthesis of CauseEffect Reasoning AND Statistical Metamodeling Paul K. Davis James H. Bigelow Prepared for the United States Air Force RAND Approved for public release distribution unlimited The research reported here was sponsored by the United States Air Force under Contract F49642-01-C-0003. Further information may be obtained from the Strategic Planning Division Directorate of Plans Hq USAF. Library of Congress Cataloging-in-Publication Data Davis Paul K. 1943- Motivated metamodels synthesis of cause-effect reasoning and statistical metamodeling Paul K. Davis James H. Bigelow. p. cm. Mr-1570. Includes bibliographical references. ISBN 0-8330-3319-0 pbk. 1. Computer simulation. 2. Decision making. I. Bigelow J. H. II. Rand Corporation. . 2003 dc21 2002155700 RAND is a nonprofit institution that helps improve policy and decisionmaking through research and analysis. RAND is a registered trademark. RAND s publications do not necessarily reflect the opinions or policies of its research sponsors. Copyright 2003 RAND All rights reserved. No part of this book may be reproduced in any form by any electronic or mechanical means including photocopying recording or information storage and retrieval without permission in writing from RAND. Published 2003 by RAND 1700 Main Street . Box 2138 Santa Monica CA 90407-2138 1200 South Hayes Street Arlington VA 22202-5050 201 North Craig Street Suite 202 Pittsburgh PA 15213-1516 RAND URL http To order RAND documents or to obtain additional information contact Distribution Services Telephone 310 451-7002 Fax 310 451-6915 Email order@ iii Preface This monograph was prepared as part of a project on multiresolution modeling for the United States Air Force Research Laboratory AFRL . The project s goal is to extend the theory and application of techniques for multiresolution multiperspective modeling MRMPM . MRMPM is of interest in many disciplines