In this work, we propose to use the class comparison methods of median absolute deviation (MAD), Significance Analysis of Microarray (SAM) and Principal Component Analysis (PCA) for selecting important genes related to survival in lymphoma gene expression profiles. MAD is applied for selecting the genes whose expression values have maximal variation across the samples. SAM identifies genes with statistically significant changes in expression by assimilating a set of gene-specific t tests. Principal Component Analysis (PCA) is a linear projection method that defines a new dimensional space (samples by principal components) that captures the maximum information present in the initial data set (samples by genes). It is demonstrated that the expression measurement of the selected genes has a strong relation to the survival time. The selected genes can be used as features in building the class predication model.