A method for robust design of products or processes with categorical response

Abstract

In many industries, quality characteristics are measured as ordered categorical responses due to measurement difficulties, or for cost-effectiveness. Although various approaches have been proposed to find robust levels of product and process design parameters when the response variable is continuous, the literature presents a limited number of studies with their own drawbacks for the ordered categorical response case. Motivated by this, we propose an alternative approach that models location and dispersion effects separately as functions of design parameters and finds settings of the parameters by considering both effects simultaneously and incorporating the decision maker’s preferences on the tradeoffs between them.

Keywords:

• Desirability function
• multi-objective optimization
• ordered categorical response
• ordinal logistic regression
• Robust parameter design

Additional information

Notes on contributors

Levent Erişkin

Levent Erişkin received BS (1998) in Industrial Engineering, MS (2003) in Operations Research and PhD (2015) in Industrial Engineering. Being a Naval Officer, he worked onboard surface ships and in Decision Support units of the Turkish Navy. He is currently Assistant Professor in Turkish Naval Academy, National Defense University. His research areas include Military Operations Research, Machine Learning and Multi Criteria Decision Making.

Leman Esra Dolgun

Leman Esra Dolgun is an Assistant Professor of Industrial Engineering Department at Eskişehir Technical University, Turkey. She received BS, MS, and PhD degrees in Industrial Engineering. Her research interests include quality engineering, design parameter optimization, Kansei engineering, univariate and multivariate statistical applications and multiple criteria decision making in quality design and improvement.

Gülser Köksal

Gülser Köksal received BS (1985), MS (1987) and PhD (1992) all in Industrial Engineering. She has been a faculty member at the Industrial Engineering Department of Middle East Technical University since 1993. She has worked as a consultant, at visiting and administrative positions for several academic and industrial organizations for total quality management, strategic planning, product planning, design optimization, technology and innovation management. Her research focuses on similar areas as well as advanced statistical applications, about which she published extensively. Her studies received awards from Informs, KalDer, and TÜSİAD.