A Method for Measuring Distance From a Training Data Set

DOI10.1080/03610920701271129MaRDI QIDQ5438322zbMATH OpenOpenAlexFDO

Authors Ilmari Juutilainen, Juha Röning

Publication date 23 January 2008

Published in Communications in Statistics: Theory and Methods (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1080/03610920701271129

zbMATH Keywords

model uncertaintydistance measurenovelty detectiondistance weighted \(k\)-nearest-neighbor

Mathematics Subject Classification ID

Applications of statistics in engineering and industry; control charts (62P30) Nonparametric inference (62G99)

Recommendations

• Discovery Science
• A distance based classification method using an incomplete training set
• Confidence Intervals for l_k,p,θ Distances
• Distance-based local linear regression for functional predictors
• Selection of Predictors in Distance-Based Regression

Cites work

• An Algorithm for Finding Best Matches in Logarithmic Expected Time
• Finding Groups in Data
• Foundations of Modern Probability
• Novelty detection: a review. I. Statistical approaches

Cited in

(1)

• Detection of correct moment to model update

This page was built for publication: A Method for Measuring Distance From a Training Data Set

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5438322)