Figure 1
From: Missing value imputation for microarray gene expression data using histone acetylation information
NRMSE performance under random model of missing values. Comparisons of NRMSE performances for KNN, LLS, GOKNN, GOLLS, knnHAI, and llsHAI in six datasets under random model of missing values. The horizontal axis is the varying range of missing percentages from 1% to 20%. The vertical axis is NRMSE of 100 independent and random test runs for each method. The knnHAI method outperforms KNN and GOKNN, while llsHAI mostly outperforms LLS and GOLLS. Generally, llsHAI performs best in most cases.