From: iRDA: a new filter towards predictive, stable, and enriched candidate genes
R-Correlation | Calculation | Applied in/to |
---|---|---|
R1: R(f i ,C) | SU i,C | \(\{\Omega _{k}\},M_{s},G\! \subseteq \!\cup _{u}{M_{s}^{p}}[\!u]\) |
 |  | ε-Estimation |
R2: R(f ij ,C) | SU i,j;C | Strongly Relevant f ij |
 |  | ε-Estimation |
R3: R(f i ,f j ) | SU i,j | ε-Estimation |
R4: R(f i ,C|M s ) | CMI (f i ,C|M s ) | Feature Redundancy |