Permutation importance, commonly used in methods like random forests, evaluates a variable’s contribution by shuffling its values and measuring the effect on prediction error. However, this approach can introduce bias due to the artificial nature of the permutations. Variable Priority (VarPro), a rule based method, addresses this issue by comparing estimates within a rule’s region to those from a release region, where variable constraints are removed. By relying entirely on observed data, VarPro offers a robust and flexible alternative that effectively filters out noise variables and avoids the pitfalls of permutation and other artificial data-based techniques.
Therefore, we developed VarPro, R software for model independent variable selection using rule based variable priority. It supports regression, classification, and survival analysis. A new mode also handles unsupervised data.
