在工業實驗的篩選實驗中，通常會考量很多可能會影響結果的因子。此時往往會使用超飽和設計（Supersaturated design）來配置實驗，此設計能夠以較少的實驗樣本個數，找出影響結果的重要因子。本文討論的超飽和設計是考慮二階交互作用下的模型參數個數比實驗樣本個數多的狀況。有鑒於一般分析方法多不考慮效應邊際準則（Functional marginality principle），我們提出三種符合效應邊際準則的方法來分析，並以模擬的方式與常用的向前選取法作比較。

Supersaturated designs are usually useful for screening experiments where the goal is to identify the few "active factors" among a potential list of design factors. The advantage of the supersaturated design is that it reduces costs by allowing using a smaller numbers of experimental runs to study many design factors. In this thesis, we consider the analysis of the supersaturated designs when the estimations of two-factor interactions as well as the main effects are of interest. We focus on the case where the number of parameters of the models containing main effects and interaction effects is greater than experimental run sizes. In this thesis we propose three analysis methods which take into account the functional marginality principle on the analysis of supersaturated designs, and compare the results with the forward selection with stimulation.

[1] Beattie, S.D., Fong, D.K.H., Lin, D.K.J., (2002). A two-stage Bayesian model selection strategy for supersaturated designs. Technometrics 44, 55-63.

[2] Booth, K. H., & Cox, D. R. (1962). Some systematic supersaturated designs. Technometrics, 4(4), 489-495.

[3] Box,G.E.P.,Meyer,R.D., 1986. An analysis for unreplicated fractional factorials. Technometrics 28,11-18.

[4] Chipman, H. (1996). Bayesian variable selection with related predictors. Canadian Journal of Statistics, 24(1), 17-36.

[5] Chipman, H., Hamada, M., & Wu, C. F. J. (1997). A Bayesian variable-selection approach for analyzing designed experiments with complex aliasing. Technometrics, 39(4), 372-381.

[6] Choi, N. H., Li, W., & Zhu, J. (2010). Variable selection with the strong heredity constraint and its oracle property. Journal of the American Statistical Association, 105(489), 354-364.

[7] Efron, B., Hastie, T., Johnstone, I., & Tibshirani, R. (2004). Least angle regression. The Annals of statistics, 32(2), 407-499.

[8] Griepentrog, G. L., Ryan, J. M., & Smith, L. D. (1982). Linear transformations of polynomial regression models. The American Statistician, 36(3a), 171-174.

[9] Hamada, M., & Wu, C. J. (1992). Analysis of designed experiments with complex aliasing. Journal of Quality Technology;(United States), 24(3).

\newpage

[10] Hao, N., Feng, Y., & Zhang, H. H. (2014). Model Selection for High Dimensional Quadratic Regression via Regularization. arXiv preprint arXiv:1501.00049.

[11] Hunter, G. B., Hodi, F. S., & Eagar, T. W. (1982). High cycle fatigue of weld repaired cast Ti-6AI-4V. Metallurgical Transactions A, 13(9), 1589-1594.

[12] Hurvich, C. M., & Tsai, C. L. (1989). Regression and time series model selection in small samples. Biometrika, 76(2), 297-307.

[13] Koukouvinos, C., & Stylianou, S. (2005). A method for analyzing supersaturated designs. Communications in Statistics—Simulation and Computation®, 34(4), 929-937.

[14] Koukouvinos, C., & Mylona, K. (2009). Group screening method for the statistical analysis of E (fNOD)-optimal mixed-level supersaturated designs. Statistical Methodology, 6(4), 380-388.

[15] Lin, D. K. (1993). A new class of supersaturated designs. Technometrics, 35(1), 28-31.

[16] Li, R., & Lin, D. K. (2002). Data analysis in supersaturated designs. Statistics & Probability Letters, 59(2), 135-144.

[17] Li, R., & Lin, D. K. (2003). Analysis methods for supersaturated design: some comparisons. Journal of Data Science, 1(3), 249-260.

[18] Nelder, J. A. (1977). A reformulation of linear models. Journal of the Royal Statistical Society. Series A (General), 48-77.

[19] Nelder, J. A. (1994). The statistics of linear models: back to basics. Statistics and Computing, 4(4), 221-234.

\newpage
[20] Phoa, F. K., Pan, Y. H., & Xu, H. (2009). Analysis of supersaturated designs via the Dantzig selector. Journal of Statistical Planning and Inference, 139(7), 2362-2372.

[21] Plackett, R. L., & Burman, J. P. (1946). The design of optimum multifactorial experiments. Biometrika, 33(4), 305-325.

[22] Satterthwaite, F. E. (1959). Random balance experimentation. Technometrics, 1(2), 111-137.

[23] Tibshirani, R. (1996). Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society. Series B (Methodological), 267-288.

[24] Wu, C. F. J. (1993). Construction of supersaturated designs through partially aliased interactions. Biometrika, 80(3), 661-669.

[25] Wu, C.F., & Hamada, M. (2009) Experiments: Planning, Analysis, and Optimization,2nd Edition. Wiley, New York.

[26] Xing, D., Wan, H., Zhu, M. Y., Sanchez, S. M., & Kaymal, T. (2013, December). Simulation screening experiments using Lasso-optimal supersaturated design and analysis: a maritime operations application. In Proceedings of the 2013 Winter Simulation Conference: Simulation: Making Decisions in a Complex World (pp. 497-508). IEEE Press.

[27] Youden, W. J., Kempthorne, O., Tukey, J. W., Box, G. E. P., & Hunter, J. S. (1959). Discussion of the papers of Messrs. Satterthwaite and Budne. Technometrics, 1(2), 157-184.