科技文明進步，固然提高了人類生活水準，但卻造成環境品質的日益惡化，近年來隨著環保意識的高漲，世界各國均開始專注環境污染問題對生態及生命所造成的影響及損害，並訂定相關的罰則以防止環境污染更進一步惡化。因此如何建立客觀的環境風險評估指標以提供作為環境品質的有效監控與事前防範的參考，便成為重要的研究課題。
近幾年來，各種單變量製程能力指標及多變量製程能力指標，已被廣泛地應用在評估生產製程表現之良窳上，但甚少學者將其應用於評估環保表現上，特別是具有多個污染變數之環境風險評估。
本研究參考現行環保標準之準則，並利用田口方法之信噪比及前置管制圖觀念，模擬建構出一環境風險警戒線，作為監控空氣及其他環境污染的標準。另外，本研究以生產製程上望小特性之製程能力指標為基礎，探討並比較其他學者所提出之多變量製程能力指標，再配合環境風險警戒線，建構出一套評估環境風險的指標。 最後，本研究以松山地區空氣品質的監測為例，說明如何利用環境風險警戒線及評估指標之對照表，可及早偵測出不同污染源對空氣品質可能的影響，以達到有效監控環境品質與事前的防範之目標。研究結果可供未來政府決策單位及業界在監控環境污染資料及評估環保表現等實務工作上時之參考。

In recent years, the recognition of environmental issues has become a global concern. With the advent of high-technology era, consumers are increasingly concerned about the environmental impact of the products they use, and major organizations and corporations around the world are starting to systematically review the environmental performance of their supplies based on the regulations stipulated by Environmental Protection Agency of each country. In order to prevent further deterioration of environmental contamination, the establishment of environmental risk assessment indices serving as a key reference for monitoring environmental performance becomes an important research topic.

Although the application of statistical process control tools to environmental process control and management has been noted before, and a few authors offer a deeper discussion of how a broad range of quality control charts can be applied to environmental management. However, both the univariate and multivariate process capability indices(to our knowledge) have not been discussed in this context before, especially the environment risk indices for assessing potential danger when several pollutants coexist.

Several multivariate process capability indices proposed by Kocherlakota and Kocherlakota(1991), Niverthi and Dey(1995), have been thoroughly discussed and compared and a table showing the frequencies of occurrence vs. five ranks of environmental risks has also been constructed.

Finally, a compute program using R language is developed to calculate the multivariate indices and a numeric example has been illustrated to show the application of these indices in early detection of air pollution in Taiwan area. Hopefully, it can provide a useful reference for the decision makers in government and industries.

1. Andrews, Gnanadesikan, and Warner, “Transformations of Multivariate Data,”
Biometrics, 27, pp.825–840(1971).
2. Bernardo, J. M. and Irony, T. Z., “A general multivariate Bayesian process
capability index,” Statistician, 45(3), pp.487-502(1996).
3. Bothe, D. R., “Composite Capability Index for Multiple Product
Characteristics,” Quality Engineering, 12(2), pp.253-258 (2000).
4. Box, G. E. P., and Cox, D. R., “An Analysis of Transformations (with
discussion),” Journal of the Royal Statistical Society, Series B, 26,
pp.211-246 (1964).
5. Chan, L. K., Cheng, S. W. and Spiring, F. A., “A New Measure of Process
Capability, Cpm,” Journal of Quality Technology, 20, pp.160-175(1988).
6. Chan, L. K., Cheng, S. W. and Spiring, F. A., “A Multivariate Measure of
Process Capability,” Journal of Modeling and Simulation, 11, pp.1-6(1991).
7. Chen, H. “A Multivariate Process Capability Index Over A Rectangular Solid
Tolerance Zone,” Statistica Sinica , 4, pp.749-758(1994).
8. Gnanadesikan, R. and Kettenring, J. R. “Robust estimates, residuals, and
outlier detection with multiresponse data,” Biometrics , 28,
pp.81-124(1972).
9. Hellmich, M. and Wolff, H., “A new Approach for Describing and controlling
process Capability for a Multivariate Process,” Proceedings of the ASA
Section on Quality and productivity, pp.44-48(1996).
10. Hubele, N. F. Shahriari, H. and Cheng, C. S, “A Bivariate Process Capability
Vector, in Statistics and Design in Process Control,” Statistical process
Control in Manufacturing edited by J. B. Keats, and D. C. Montgomery. Marcel
Dekker, New York, NY. pp.299-310(1991).
11. Johnson, N. L., “Systems of Frequency Curves Generated by Methods of
Translation,” Biometrika, 36, pp. 149-176(1949).
12. Juran, J. M., Quality Control Handbook, 3rd edition, McGraw-Hill, New York
(1974).
13. Kane, V. E., “Process Capability indices,” Journal of Quality Technology,
18, pp.41-52(1986).
14. Krishnamoorthi, K. S., “Capability Indices for Processes Subject to
Unilateral and Positional Tolerances,” Quality Engineering, 2, pp.461-471
(1990).
15. Kocherlakota, S. and Kocherlakota, K., “Process capability index: Bivariate
normal distribution,” Commun. Statist. – Theory Method., 20(8),
pp.2529-2547 (1991).
16. Kotz., S. and Lovelace, C. R., “Process Capability Indices in Theory and
Practice, Chapman and Hall, London, U. K.(1998).
17. Kotz., S. and Johnson, N. L., “Process Capability Indices—A Review,
1999-2000,” Journal of Quality Technology, 34(1), pp.2-19(2002).
18. Li, Y. and Lin, C., “Multivariate Cp Value,” Chinese Journal of Applied
Probability and Statistics, 12, pp.132-138(1996).
19. Mardina, K.V. “Measures of multivariate skewness and kurtosis with
applications,” Biometrika, 57, pp.519-530(1970).
20. Niverthi, M. and Dey, D. K., “Multivariate process capability: a Bayesian
perspective”. Technical Report, Dept. of Statistics, University of
Connecticut, Storrs(1995).
21. Littig, S. J., Lam C. T. and Pollock, S. M., “Capability measurements for
multivariate processes: Definition and an example for a gear carrier,”
Technical Report, 92-42, Dept. of Industrial and Operations Engineering,
Univ. of Michigan, Ann Arbor, MI(1992).
22. Ott, W. R., Environmental Indices: Theory and Practice, Ann Arbor Science
Publishers Inc., pp.365, Ann Arbor, MI(1978).
23. Pan, J. N. and Corbett, C. J., “Evaluation of the environmental performance
using statistical process control techniques,” Technical Report, School of
Management, UCLA(2000).
24. Pearn, W. L., Kotz, S. and Johnson, N. L., “Distribution and Inferential
Properties of Process Capability Indices,” Journal of Quality Technology,
24, pp.216-231(1992).
25. Shahriari, H., Hubele, N. F., Lawerence, F. “A Multivariate Process
Capability Vector,” preswnted at the 4th Industrial Engineering Research
conference, Nashville, TN, May 24(1995).
26. Spiring, F. A., “The Reflected Normal Loss Function,” The Canadian Journal
of Statistics, 21, pp.321-330(1993).
27. Taguchi, G.., Introduction to Quality Engineering: Designing Quality Into
Products and Processes, Asian Productivity Organization, Tokyo(1986).
28. Taam, W., Subbaiah, P., and Liddy, J. W., “A Note on Multivariate Capability
Indices,” Journal of Applied Statistics, 20, pp.339-351(1993).
29. Veevers, A., “A Capability Index for Multiple Response”, CSIRO Mathematics
and Statistics Report DMS-095, Australia(1995).
30. Wang,F. K., Hubele, N. F., Lawrence, P. F., Miskulin, J. D. and Shahriari,
H., ”Comparison of Three Multivariate Process Capability Indices,” Journal
of Quality Technology , 32, pp.263-275(2000).
31. Wierda, S. J., “Multivariate Quality Control- Estimation of the percentage
of good products.” Technical Repot, Dept. of Econometrics, University of
Groningen, The Netherlands(1992).
32. Yeh, A. B. and Chen, H., “A Nonparametric Multivariate Process Capability
Index,” Preprint.(1999).