A nonparametric variance-stabilizing transformation method in cDNA microarray

• Main Authors: Hsiang-Yu Chung, 鍾翔宇
• Other Authors: Shin-Huang Chan
• Format: Others
• Language: zh-TW
• Published: 2006
• Online Access: http://ndltd.ncl.edu.tw/handle/32065043145865846984

碩士 === 國立成功大學 === 統計學系碩博士班 === 94 === For cDNA microarray data, the variance of gene is usually not the same and depends on its mean. Durbin et al. (2002) and Inoue et al. (2004) established the one-color gene expression model and obtain the relationship between variance of gene and its mean. They then derive the variance-stabilizing transformation function to stabilize the variance of the genes. 　In this article, we consider the two-color design and use nonparametric regression approach to stabilize the variance of gene expression level. We first, by applying lowess method, find the relationship between variance and mean of gene expression from scatter plot of variance versus mean, then use exponential function to approximate the relationship between variance and mean in a small region. Simulation study and real data analysis show that the performance of the suggested method is comparable to the parametric variance stabilization approach when the variance function is known.