Communications for Statistical Applications and Methods

Indexed in /covered by CAS, KoreaScience & DOI/Crossref:eISSN 2383-4757   pISSN 2287-7843

Fig. 2.

Download original image
Fig. 2. Boxplots of log10(p)-values for simulation study tests of pathway disturbance. Network structure is a binary tree. X (shown in blue) represents EMC-NetGSA applied to the complete data matrix, with no missing values. X̃ is the matrix with all samples with any missing values dropped. I3 (in green) refers to our integrated, iteratively imputed matrix. SMC uses imputed values obtained by treating the entire minimal covering submatrix as missing, and KNN is K = 10-nearest neighbors imputation. Horizontal line gives log10(0.05). Scenario 1 (left): No features differential. Scenario 2 (right): Top 2/3 features differential.
Communications for Statistical Applications and Methods 2019;26:411-30 https://doi.org/10.29220/CSAM.2019.26.4.411
© 2019 Communications for Statistical Applications and Methods