Model tuning in engineering: Uncovering the logic

Steele, Katie and Werndl, Charlotte (2015) Model tuning in engineering: Uncovering the logic. [Preprint]

PDF
JSAReviseFinal.pdf
Download (219kB)

Official URL: http://sdj.sagepub.com/content/early/2015/03/20/03...

Abstract

In engineering, as in other scientiﬁc ﬁelds, researchers seek to conﬁrm their models with real-world data. It is common practice to assess models in terms of the distance
between the model outputs and the corresponding experimental observations. An important question that arises is whether the model should then be "tuned", in the sense of estimating the values of free parameters to get a better ﬁt with the data, and furthermore whether the tuned model can be conﬁrmed with the same data used to tune it. This dual use of data is often disparagingly referred to as "double-counting". Here we analyse
these issues, with reference to selected research papers in engineering (one mechanical, the other civil). Our example studies illustrate more and less controversial practices of model tuning and double-counting, both of which, we argue, can be shown to be legitimate within a Bayesian framework. The question nonetheless remains as to whether the implied scientiﬁc assumptions in each case are apt from the engineering point of view.

Export/Citation:

Social Networking:

Share |

Item Type:

Preprint

Creators: