Efficient permutation testing of variable importance measures by the example of random forests

• Published in: Computational statistics & data analysis Vol. 181; p. 107689
• Main Authors: Hapfelmeier, Alexander, Hornung, Roman, Haller, Bernhard
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.05.2023
• Subjects: data analysis; Machine learning; p-value; prediction; Prediction model; probability; Sequential permutation test; Variable selection; p-value; Sequential permutation test; Prediction model; Machine learning; Variable selection

Hypothesis testing of variable importance measures (VIMPs) is still the subject of ongoing research. This particularly applies to random forests (RF), for which VIMPs are a popular feature. Among recent developments, heuristic approaches to parametric testing have been proposed whose distributional...