Statistical Analysis of Simulation Output Data

Article Abstract:

A large amount of money is spent on model development and programming. Little effort is made to analyze the simulation output data. Random samples from probability distributions are typically used, and large variances can occur. Often only one computer simulation is run and conclusions formed. In fact, however, a simulation is a computer-based statistical sampling experiment. Therefore appropriate statistical techniques must be used. A state-of-the-art treatment of statistical analyses of simulation output data is given. The material is presented with a practical focus that should be accessible to a reader having a basic understanding of probability and statistics.

Continuous Simulation, Discrete Simulation, Data Analysis, Markov Process, Variance Reduction

---

The Integrated Simulation Environment (Simulation Software of the 1990s)

Article Abstract:

Projected improvements that will be made in simulation software are analyzed. The basic focus is on computer programming. A computer simultation model can be programmed in a simulation language or a non-simulation language. The cost of programming is rapidly rising. Model definition languages and model editors are improving and the framework of a modeling methodology of the future has been defined. A variety of techniques have been used to solve the problems of translating high level model descriptions into simulation language source code. Statistics and subroutine packages have been implemented in some languages.

Software, Computers, Digital computers, Technological forecasting, Mathematical software, Statistical software, Language, Future of Computing, Statistical/Mathematical Software

---

An Analytical Evaluation of Alternative Strategies in Steady- State Simulation

Article Abstract:

Independent and probabilistic identical simulation replications are used to estimate the steady-state mean of a stochastic process. Furthermore, deletion can be an effective and efficient tool for reducing bias caused by artificial startup conditions. Replication is simple to use. Graphs are used to present computational results.

Mathematical models, Algorithms, Algorithm, Estimation, Stochastic Model, Algorithm Analysis

Similar abstracts:

• Abstracts: The economic theory of regulation versus alternative theories for the electric utilities industry: a simultaneous probit model
• Abstracts: Accelerated Accuracy in the Simulation of Markov Chains. Accelerated Convergence in the Simulation of Countably Infinite State Markov Chains
• Abstracts: A Class of Variance Constrained Problems. The Solution of Distance Constrained Mini-Sum Location Problems. Two Algorithms for Constrained Two-Dimensional Cutting Stock Problems
• Abstracts: Modeling and Analysis of Three-Stage Transfer Lines with Unreliable Machines and Finite Buffers. A Unifying View of Hybrid Simulation-Analytic Models and Modeling
• Abstracts: Radiotherapy Treatment Design Using Mathematical Programming Models. Mathematical Pitfalls in the One Machine Multiproduct Economic Lot Scheduling Problem

This website is not affiliated with document authors or copyright owners. This page is provided for informational purposes only. Unintentional errors are possible.