- 【Updated on May 12, 2025】 Integration of CiNii Dissertations and CiNii Books into CiNii Research
- Trial version of CiNii Research Knowledge Graph Search feature is available on CiNii Labs
- 【Updated on June 30, 2025】Suspension and deletion of data provided by Nikkei BP
- Regarding the recording of “Research Data” and “Evidence Data”
Application of Calibrated Error Variance to the RT Method
-
- Yano Koya
- 日本大学,正会員
-
- Hayakawa Yukihiro
- 富山商船高等専門学校,正会員
-
- Kamoshita Takashi
- 応用計測研究所(株),正会員
Bibliographic Information
- Other Title
-
- 標準化誤圧を応用したRT法
- -パターン距離を利用しない解析-
- -Analysis without Using Pattern Distance-
Search this article
Description
<p>The Recognition-Taguchi(RT) method is useful because, as itcollects items into the two variables β(sensitivity) and η(signal-to-noise ratio), a pattern distance can be obtained even when the number of original data items is greater than the number of unit space data items n, and because the dimensional reduction yields a solution even when the true values are unknown. In this study, however,the concept of the calibrated error variance proposed by Dr. Taguchi was applied. An attempt was made to calculate a general scale similar to the distance obtained by the RT method from the variation/variance ratio by use of analysis of variance, without calculating distances. Results matching the results of the RT method were obtained. In addition, it became clear that because analysis of variance is used, there is no limit on the number of items,which constrains matrix calculations, and the data can be treated in the same way as in the RT method.</p>
Journal
-
- Journal of Quality Engineering Society
-
Journal of Quality Engineering Society 18 (5), 73-80, 2010
Robust Quality Engineering Society
- Tweet
Keywords
Details 詳細情報について
-
- CRID
- 1390282680740484480
-
- NII Article ID
- 130005431112
-
- ISSN
- 21899320
- 2189633X
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
- CiNii Articles
-
- Abstract License Flag
- Disallowed