Comparative study of the Cp and Spmk indices for logistic regression profile using different link functions. Issue Volume 31:Issues 3(2019) (3rd July 2019)

• Record Type: Journal Article
• Authors: Alevizakos, Vasileios; Koukouvinos, Christos; Lappa, Angeliki
• Is Part Of: Quality engineering. Volume 31:Issues 3(2019)
• Page Start: 453
• Page End: 462
• Publication Date: 2019-07-03
• Subjects: Link function -- logistic regression profile -- process capability index -- profile monitoring; Quality control -- Periodicals; Production management -- Quality control -- Periodicals; 658.5
• DOI: 10.1080/08982112.2018.1523427
• Languages: English
• ISSNs: 0898-2112

Abstract

Abstract: In some process control applications, the quality of a process or a product can be characterized by a relationship between a response variable and one or more independent variables which is typically referred to as a profile. For an in-control process, process capability indices are widely used for the characterization of the capability of a process. Although there are several studies in monitoring profiles, there are a few studies to evaluate the process capability of the profiles. In the majority of cases, the response variable in the profile follows a normal distribution, but, sometimes, this assumption is violated. In many industrial applications, the response variable is binary or binomial, as in the case of whether a product can be classified as defective or nondefective. In this article, we calculate the C p and S pmk indices to measure the process capability when the quality of a process is characterized by a logistic regression profile with three well-known link functions, the logit, the probit and the complementary log-log.