Gauge Variation Study for Ordinal Data

• Main Authors: Chia-Chi Kuo, 郭家吉
• Other Authors: Jeh-Nan Pan
• Format: Others
• Language: zh-TW
• Published: 2007
• Online Access: http://ndltd.ncl.edu.tw/handle/36277503622344684780

碩士 === 國立成功大學 === 統計學系碩博士班 === 95 === Recently, gauge variation study has been highly regarded by the quality practitioners when QS9000 and TS16949 become fashionable requirements for manufacturing industries. Measurement plays a significant role in helping organizations improve their product quality. Good quality of products is the key factor of business success. Therefore, how to ensure the quality of measurement becomes an important task for the quality practitioners. Gauge variation study can be divided into two parts by data types; continuous data and attribute data. Especially, attribute data also can be divided into three parts; ordinal data, binary data and the data follows Poisson distribution. Therefore, the main purpose of this research lays stress on ordinal data. In food industries, sensory evaluation is increasing in importance because of the present economic emphasis on consumer needs and wants. However, the consistency within panelists and between panelists may affect the reliability of sensory evaluation. Therefore, in performing the gauge variation study for ordinal data, most food industries are using Kappa and Kendall concordant coefficient stipulated by QS9000. A comparative analysis has been conducted for evaluating the accuracy of gauge variation study among two methods (Kappa and Kendall). Moreover, the rationale for a proper choice of the number of panelists (b), the sample size (n) and replicate measurement (r) is discussed. Hopefully, it can provide a useful reference for the food industries.