| Summary: | 碩士 === 國立中正大學 === 數學系統計科學研究所 === 104 === In recent Statistical Procss Control (SPC) applications, a manufacturing process or product is characterized by a profile, which is a functional relationship between a response variable and one or more explanatory variables over time. The presence of outliers has seriously adverse effects on the modeling, monitoring, and forecasting of profile data. Hence, in the SPC profile problem, it becomes cruical to identify outlying profiles among a set of complex profiles and to remove them from the reference dataset. To this end, in this thesis, we propose an iteration influence function control chart to detect outlying profiles. We also compare our proposed method with $\chi^2$ control chart method in Zhang and Albin (2009) and penalized profile outlier detection revised (PPOD-R) method proposed by Zou et al. (2012). Simulation studies and a real data example are provided for illustration.
|
|---|
