Microarray實驗涉及到許多的步驟，每一個環節皆可能存在變異。此等變異若未加以移除，將造成資料偏頗，使我們對基因的功能解讀錯誤，而得到不正確的結論。如何控制microarray實驗的變異，以確保microarray資料的品質，便成為分析microarray資料前必需要做的前置處理工作。本文對有重複測量值的資料，就Dudoit et al. (2001)所提出之lowess normalization的想法，建議一更適當的normalization方式。我們以模擬的方式評估所建議之noramlzation法的優劣，並以膀胱癌microarray資料做為所建議之方法的實例應用。

Microarray experiment involves many steps, and for each step there may exist systematic variation. In order to making correct decision, this systematic bias has to be identified and be removed before analyzing data. Based on the concept of lowess normalization process suggested by Dudoit et al. (2001), a more appropriate normalization method would be presented in this thesis to deal with genes with replicate expressions. Simulation study shows that the performance of the suggested normalization method is superior to the available approaches. We use a microarray data for bladder cancer supplied by National Cheng Kung University Hospital to illustrate the application, and use real-time PCR to evaluate the performance of our approach.

[1] Benjamini, Y., and Hochberg, Y. (1995). Controlling the false discovery rates: A practical and powerful approach to multiple testing. Journal of the Royal Statistical Society, Ser. B 57, 289-300.
[2] Dudoit, S., Fridlyand, J., and Speed, T. P. (2002). Comparison of discrimination methods for the classification of tumors using gene expression data. Journal of the American Statistical Association, 97, 77-87.
[3] Dudoit, S., Yang, Y. H., Speed, T. P., and Callow, M. J. (2002). Statistical methods for identifying differentially expressed genes in replicated cDNA microarray experiments. Statistica Sinica, 12,111-140.
[4] Efron, B. and Tibshirani, R. (2002). Empirical Bayes methods and false discovery rates for microarrays. Genetic Epidemiology, 23, 70-86.
[5] Efron, B., Tibshirani, R., Storey, J. D. and Tusher, V. (2001). Empirical Bayes analysis of a microarray experiment. Journal of the American Statistical Association, 96, 1151-1160.
[6] Kerr, M. K., Afshari, C. A. et al. (2002). Statistical analysis of a gene expression microarray experiment with replication. Statistica Sinica, 12, 203-217.
[7] Laura, J., Veer, V. et al. (2002). Gene expression profiling predicts clinical outcome of breast cancer. Nature, 415, 530-536.
[8] Lee, M., Kuo, F., Whitmore, G., and Sklar, J. (2000). Importance of replication in microarray gene expression studies: Statistical methods and evidence from a single cDNA array experiment. Proceedings National Academy of Science, 97, 9834-9839.
[9] Simon R., Radmacher M. D., Dobbin. (2002). Design of studies using DNA microarrays. Genetic Epidemiology, 23, 21-36.
[10] Tusher, V. G., Chu, G. and Tibshirani, R. (2001). Significance analysis of microarrays applied to the ionizing radiation response. Proceedings National Academy of Science, 98, 5116-5121.
[11] Yang,Y. H., Buckley, M. J., Dudoit, S., and Speed, T. P. (2002). Comparison methods for image analysis on cDNA microarray data. Journal of Computational and Graphical Statistics, 11, 108-136.
[12] Yang, Y. H., Dudoit, S., Luu, P., and Speed, T. P. (2001). Normalization for cDNA microarray data. In M. L. Bittner, Y. Chen, A. N. Dorsel, and E. R. Dougherty (eds.), Microarrays: Optical Technologies and Informatics, Volume 4266 of Proceedings of SPIE.