Statistical method for proficiency tests with uncertainty information

2015 Fiscal Year Final Research Report

• Project/Area Number: 26870899
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Statistical science; Social systems engineering/Safety system
• Research Institution: National Institute of Advanced Industrial Science and Technology
• Principal Investigator: Shirono Katsuhiro 国立研究開発法人産業技術総合研究所, 物質計測標準研究部門, 主任研究員 (60509800)
• Project Period (FY): 2014-04-01 – 2016-03-31
• Keywords: 技能試験 / 不確かさ / En数 / モデル選択

Outline of Final Research Achievements

We propose the novel method to evaluate performance of testing laboratories through an interlaboratory comparison, given uncertainty information. An interlaboratory comparison indicates a test in which some laboratories measure an identical item. An uncertainty means the quantified value of the reliability of reported measurement value. In this study, a two-step analysis method is proposed. In the first step, the model selection technique is applied to check the validity of the planning and the implementation of an interlaboratory comparison. In the second step, the performances of the laboratories are evaluated based on the selected model. The fast and precise computation algorithm is developed for the both steps. This analysis could be helpful to secure the fairness in the proficiency evaluation of a testing laboratory.

Free Research Field

情報学・複合領域