隨著高科技產品越來越精密，其製造過程的複雜度、花費的時間以及成本也越來越高。因此，對於這種高成本製程的產品而言，監控製程抽樣往往每次只能得到一個觀測值。另外，一個製程可能需要同時監控多個相關的品質特徵。因此，在這種情況之下，在第一階段的分析中要精確地估計出穩定製程參數的難度更高了。而本文主要在共變異數矩陣不會改變的假設下，來對單一觀測值的製程平均數向量來進行第一階段的監控。我們以現行的一些T^2 監控統計量結合近年來生物統計界盛行的錯誤發現率來做為監控的準則，並且以統計模擬來比較這種準則和各種T2管制圖的優劣。在過去的文獻中，失控警訊機率往往被當作比較不同監控方法優劣的基準，在此，我們發現不能只以失控警訊機率做為比較的準則，還需將正確拒絕率和錯誤拒絕率列入考量才行。

[1] Benjamini, Y. and Hochberg, Y., (1995), “Controlling the False Discovery Rate: a Practical and Powerful Approach to Multiple Testing,”Journal of the Royal Statistical Society B, 57, 289-300.
[2] Hawkins, D. M. (1994). “A Feasible Algorithm for the Minimum Covariance Determinant Estimator in Multivariate Data.” Computational Statistic and Data Analysis, 8 197-210.
[3] Jesen, W. A., Birch, J. B., and Woodall. W. H., (2007), “High Breakdown Estimation Method for Phase I Multivariate Control Charts,” To appear in Quality and Reliability Engineering International.
[4] Pison, G., Van Aelst, S. and Willems, G. (2002), “Small Sample Corrections for LTS and MCD,” Metrika, 55, 111-123.
[5] Rousseeuw, P. J. (1984), “Least Median of Squares Regression,” Journal of American Statistical Association, 79, 871-880.
[6] Rousseeuw, P. J. and VAN Driesson, K (1999), “A Fast Algorithm for the Minimum Covariance Determinant Estimate,” Technometrics, 41,293-305.
[7] Rousseeuw, P. J. and van Zomerern, B. C. (1990), “Unmasking Multivariate Outlier and Leverage Ponits,” Journal of the American Statistical Association, 85, 633-639.
[8] Sullivan, J. H. and Woodall W. H. (1996), “A Comparison of Multivariate Quality Control Charts for Individual Observations,” Journal of Quality Technology, 28, 398-408.
[9] Vargas, J. A. (2003), “Robust Estimation on Multivariate Control Charts for Individual Observations,” Journal of Quality Technology, 35,367-376.