Choosing the best model: Level of detail, complexity, and model performance
Choosing the best model: Level of detail, complexity, and model performance
复制标题
DOI：
10.1016/0895-7177(96)00103-3
复制
发表时间：
1996-08-01
影响因子：
--
通讯作者：
Tobias, AM
中科院分区：
文献类型：
--
作者：
Brooks, RJ;Tobias, AM
在数学或计算机建模研究中缺乏选择最佳模型的方法，或者至少是详细的指导方针，是因为对研究的成功取决于所使用的特定模型的精确方式缺乏了解。因此，最佳模型的选择更多地被视为一门艺术而不是一门科学。为了改进模型选择过程，需要明确定义模型性能，并确定可用于预测替代候选模型性能的合适模型属性。本文区分了模型性能的不同方面，并考虑了它们可以测量的程度。用于比较替代模型的最常见属性是细节级别和复杂性，尽管这些术语有多种不同的使用方式。因此，讨论了这些概念的含义，并考虑了与模型性能元素的可能关系。审查了相关的简化领域，并列出了需要进一步工作的领域。
The lack of a methodology, or at least detailed guidelines, for choosing the best model in a mathematical or computer modelling study stems from a poor understanding of the precise ways in which the success of the study depends upon the particular model used. As a result, the choice of the best model is regarded as more of an art than a science. In order to improve the model selection process, model performance needs to be clearly defined, and suitable model attributes identified that can be used to predict the performance of the alternative candidate models. This paper distinguishes the different aspects of model performance and considers the extent to which they can be measured. The most common attributes used to compare alternative models are level of detail and complexity although these terms are used in a number of different ways. The meanings of these concepts are therefore discussed and the likely relationships with the model performance elements considered. The related area of simplification is reviewed and the areas in which further work is required are set out.