Showing papers on "Verification and validation of computer simulation models published in 1972"
TL;DR: The philosophical questions of model validity and the need for practical tests of the adequacy and representativeness of computerized simulation models are reviewed and the distinction between the concepts of the verification and the validation of such general models is made.
Abstract: This paper reviews the philosophical questions of model validity and describes the need for practical tests of the adequacy and representativeness of computerized simulation models. The distinction between the concepts of the verification and the validation of such general models is made by means of a delineation of test procedures, primarily those of a statistical nature, which are applicable to the determination of a simulation model's adequacy.
108 citations
TL;DR: An argument is established that questions the validity of one "test" of goodness-of-fit for the simulated time path of a single endogenous variable in a simultaneous, perhaps dynamic, econometric model.
Abstract: This paper establishes an argument that questions the validity of one “test” of goodness-of-fit for the simulated time path of a single endogenous variable in a simultaneous, perhaps dynamic, econometric model. The test was suggested by Cyert and Cohen, and consists of two parts, within the context of a regression of the actual series on the generated series: a test that the intercept of this regression differs significantly from zero and a test that the slope of this regression differs significantly from one. Presumably, the intuition underlying the test is that if the simulation model is a good one this regression should be a 45° line through the origin. The paper's primary purpose is to demonstrate that this intuition is wrong in general for the case of “stochastic simulation.”
26 citations
TL;DR: The interrelationships between models and other methods for evaluating the performance of computer systems are examined and circumstances under which the use of a model is appropriate are established.
Abstract: Models constitute a useful means of investigating computer system performance. This paper examines the interrelationships between models and other methods for evaluating the performance of computer systems and establishes circumstances under which the use of a model is appropriate.
22 citations
TL;DR: This paper considers the problems involved in the validation and calibration of several classes of simulation models, and distinctions are drawn between validation procedures appropriate to discrete-event and continuous-simulation models and to dynamic and cross-sectional structures in the systems modelled.
Abstract: The validation of simulation models is not often treated to any great depth in reports on their use This paper considers the problems involved in the validation and calibration of several classes of simulation models Particular stress is laid on the checking of the internal consistency of the model against the problem as posed by the model designer Distinctions are drawn between fitting, calibration, and validation of a model, and some of the implica tions for forecasting using such a model are discuss ed Systematic errors may be introduced in any of these stages, and it is argued that the estimation of their magnitude is an intrinsic part of the validation process Distinctions are drawn between validation procedures appropriate to discrete-event and continuous-simulation models, and to dynamic and cross-sectional structures in the systems modelled
20 citations
TL;DR: The rationale for the systematic development of a simulation model and the concomitant data collection program is presented and should be useful for managing difficult simulation studies.
Abstract: Simulation models are commonly resolved in time and space beyond the integrity of available field observations. Input data are fudged accordingly, and, ultimately, expensive simulation models coexist with inadequate data bases. Such manipulation is necessary in sensitivity analysis, but a compromise between data collection and model extrapolation must be found. The rationale for the systematic development of a simulation model and the concomitant data collection program is presented in this paper and should be useful for managing difficult simulation studies.
6 citations
01 Jul 1972
TL;DR: In this paper, a systematic logic for the validation of digital simulation models is presented and applied to validate a previously developed model for simulating the acts and behaviors of intermediate size crews as they perform system operation tasks.
Abstract: : A systematic logic for the validation of digital simulation models is presented and applied to the validation of a previously developed model for simulating the acts and behaviors of intermediate size crews as they perform system operation tasks. The mission simulated was a trust territories reconnaissance by a patrol gunboat (PG) class Navy ship. The results indicated that the validation logic employed (the multimethod-multitrait approach) aided in the identification of both model and criterion error. Identification of both error sources is required if model improvements and revisions are to be implemented. The results of the various analyses, completed on the basis of an initial multimethod-multitrait matrix, indicated support for both the convergent and the discriminant validity of the simulation model. (Author)
1 citations
Journal Article•
TL;DR: The choice and the form of the model is determined by the specific application and the accuracy required as discussed by the authors, which is dependent on the knowledge gained from mathematical models, and the choice and form of a model are determined by specific application.
Abstract: Prediction and simulation are dependent on the knowledge gained from mathematical models. The choice and the form of the model is determined by the specific application and the accuracy required. Model techniques, such as horizontal oscillation tests, provide the means of finding the coefficients of extensive non-linear models, though for other purposes, such as simulation, there is also a need for simpler, empirical models. To determine the coefficients of such models, free-running full-scale or model tests are necessary.
1 citations