skip to main content

SciTech ConnectSciTech Connect

Title: Comment: Spurious Correlation and Other Observations on Experimental Design for Engineering Dimensional Analysis

This article discusses the paper "Experimental Design for Engineering Dimensional Analysis" by Albrecht et al. (2013, Technometrics). That paper provides and overview of engineering dimensional analysis (DA) for use in developing DA models. The paper proposes methods for generating model-robust experimental designs to supporting fitting DA models. The specific approach is to develop a design that maximizes the efficiency of a specified empirical model (EM) in the original independent variables, subject to a minimum efficiency for a DA model expressed in terms of dimensionless groups (DGs). This discussion article raises several issues and makes recommendations regarding the proposed approach. Also, the concept of spurious correlation is raised and discussed. Spurious correlation results from the response DG being calculated using several independent variables that are also used to calculate predictor DGs in the DA model.
Publication Date:
OSTI Identifier:
Report Number(s):
DOE Contract Number:
Resource Type:
Journal Article
Resource Relation:
Journal Name: Technometrics, 55(3):286-289
Research Org:
Pacific Northwest National Laboratory (PNNL), Richland, WA (US)
Sponsoring Org:
Country of Publication:
United States
Dimensional analysis; model-robust experimental design; Spurious correlation.