期刊
TECHNOMETRICS
卷 51, 期 4, 页码 366-376出版社
AMER STATISTICAL ASSOC
DOI: 10.1198/TECH.2009.08040
关键词
Curse of dimensionality; Effect sparsity; Gaussian process; Latin hypercube design; Prediction accuracy; Random function
资金
- Natural Sciences and Engineering Research Council of Canada
We provide reasons and evidence supporting the informal rule that the number of runs for an effective initial computer experiment should be about 10 times the input dimension. Our arguments quantify two key characteristics of computer codes that affect the sample size required for a desired level of accuracy when approximating the code via a Gaussian process (GP). The first characteristic is the total sensitivity of a code output variable to all input variables; the second corresponds to the way this total sensitivity is distributed across the input variables, specifically the possible presence of a few prominent input factors and many impotent ones (i.e., effect sparsity). Both measures relate directly to the correlation structure in the GP approximation of the code. In this way, the article moves toward a more formal treatment of sample size for a computer experiment. The evidence supporting these arguments stems primarily from a simulation study and via specific codes modeling climate and ligand activation of G-protein.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据