PCA-based high-dimensional noisy data clustering via control of decision errors
Knowledge-Based Systems
| Hi-index | 12.05 |
Classifying genes with time-course expression data into one of the several predefined patterns is viewed as a multiple significance testing problem. The proposed approach calculates the p-value of test statistic using the Monte Carlo method and classifies genes by controlling the overall false discovery rate. We also estimate the positive false discovery rate of each pattern. The proposed procedure was applied to a real data set and some numerical experiments using synthetic data are performed.