Power analysis for group supplier selection with multiple production lines

W.l. Pearn, Y. T. Tai*, Yu Wen Wu, Yuan An Wang

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

5 Scopus citations


Group supplier selection problem is a critical problem because outsourcing is an important issue for supply chain management. For the advanced production processes with extremely low fraction of defectives, typical supplier selection methods no longer work because any sample of reasonable size probably contains no defective items. Thus, process capability indices have been extensively used for advanced production processes to evaluate and measure whether the process meets the specifications and they also provide quality assurance. In the globally competitive production environment, processes involving multiple production lines are quite common due to economies of scale considerations. In this paper, we consider a group supplier selection problem for multi-supplier and multi-line, in which a supplier group containing the best suppliers is selected based on a multi-line yield index CM pk To avoid the inflation of multiple comparisons, we apply the Bonferroni method and subtraction test statistic to tackle the group supplier selection problem. Critical values for testing procedure and required sample sizes for designated selection powers are obtained and tabulated. In addition, we apply multiple comparisons with the best method and compare the selection powers with the Bonferroni method for various power settings to provide more accurate group supplier decisions for real-world applications.

Original languageEnglish
Pages (from-to)1530-1543
Number of pages14
JournalQuality and Reliability Engineering International
Issue number8
StatePublished - 1 Dec 2018


  • capability index
  • multiple lines
  • power
  • supplier selection

Fingerprint Dive into the research topics of 'Power analysis for group supplier selection with multiple production lines'. Together they form a unique fingerprint.

Cite this