It has been our observation that in many simulation studies a large amount of time and money is spent on model development and programming, but little effort is made to analyze the simulation output data in an appropriate manner. As a matter of fact, a common mode of operation is to make a single simulation run of somewhat arbitrary length and then treat the resulting simulation estimates as being the "true" answers for the model. Since these estimates are random variables which may have large variances, these estimates may, in a particular simulation run, differ greatly from the corresponding true answers. The net effect is, of course, that there may be a significant probability of making erroneous inferences about the system under study.
One reason for the historical lack of definitive output data analyses is that simulation output data are rarely, if ever, independent. Thus, classical statistical analyses based on independent identically distributed observations are not directly applicable. At the present time, there are still several output analysis problems for which there is no completely accepted solution, and the solutions that do exist are often complicated to apply. Another impediment to getting accurate estimates of a model's true parameters or characteristics is the computer cost associated with collecting the necessary amount of simulation output data. Indeed, there are situations where an appropriate statistical procedure is available, but the cost of collecting the amount of data dictated by the procedure is prohibitive. We expect this latter problem to become less important as the cost of computer time continues to drop.
Our goal in this talk is to give a state-of-the-art treatment of statistical analyses for simulation output data, and to present the material with a practical focus which should be accessible by a reader having a basic understanding of statistics. The emphasis will be on statistical procedures which are relatively easy to understand and apply, have been shown to perform well in practice, and have applicability to real-world problems.
Most of the material presented in this talk may be found in Law and Kelton (1981).
我们已经观察到,在许多仿真研究中,模型开发和编程花费了大量时间和金钱,但很少花费精力以适当的方式分析仿真输出数据。实际上,一种常见的操作模式是进行某种程度任意长度的单次模拟运行,然后将所得的模拟估计值视为该模型的“真实”答案。由于这些估计是可能具有较大方差的随机变量,因此在特定的模拟运行中,这些估计可能与相应的真实答案有很大差异。当然,最终的结果是,可能有很大的可能性对所研究的系统做出错误的推论。 P>
历史上缺乏确定的输出数据分析的一个原因是,模拟输出数据很少(如果有的话)是独立的。因此,基于独立的均匀分布观测值的经典统计分析不能直接应用。目前,仍然存在一些输出分析问题,尚无一个完全可接受的解决方案,而且存在的解决方案通常很难应用。获得对模型的真实参数或特性的准确估计的另一个障碍是与收集必要数量的模拟输出数据相关的计算机成本。确实,在某些情况下可以使用适当的统计程序,但是收集由该程序指定的数据量的成本令人望而却步。我们希望随着计算机时间成本的持续下降,后一个问题将变得不那么重要。 P>
我们在本次演讲中的目标是为模拟输出数据提供最新的统计分析方法,并提出具有实际重点的材料,对统计学有基本了解的读者应该可以访问该材料。 。重点将放在相对容易理解和应用的统计程序上,这些程序已被证明在实践中表现良好,并且适用于现实世界中的问题。 P>
本演讲中介绍的大部分材料都可以在Law和Kelton(1981)中找到。 P>
机译:模拟输出数据的统计分析:实际情况
机译:使用上个千年的气候替代数据评估气候模型模拟的统计框架-第3部分:实际考虑,宽松的假设以及使用树轮数据解决太阳强迫的幅度
机译:使用上个千年的气候替代数据评估气候模型模拟的统计框架–第3部分:实际考虑,宽松的假设以及使用年轮数据解决太阳强迫的幅度
机译:仿真输出数据的统计分析:现有技术
机译:根据输入输出数据的离散值实际识别线性系统。
机译:循环统计遇到实际限制:基于模拟的Rao对非连续数据的间隔测试
机译:仿真输出数据的统计分析:现有技术