The Annals of Statistics

An Algorithm for Isotonic Regression for Two or More Independent Variables

Richard L. Dykstra and Tim Robertson

Full-text: Open access

Abstract

Algorithms for solving the isotonic regression problem in more than one dimension are difficult to implement because of the large number of lower sets present or because they involve search techniques which require a significant amount of checking and readjustment. Here a new algorithm for solving this problem based on a simple iterative technique is proposed and shown to converge to the correct solution.

Article information

Source
Ann. Statist., Volume 10, Number 3 (1982), 708-716.

Dates
First available in Project Euclid: 12 April 2007

Permanent link to this document
https://projecteuclid.org/euclid.aos/1176345866

Digital Object Identifier
doi:10.1214/aos/1176345866

Mathematical Reviews number (MathSciNet)
MR663427

Zentralblatt MATH identifier
0485.65099

JSTOR
links.jstor.org

Subjects
Primary: 65D15: Algorithms for functional approximation
Secondary: 49D05

Keywords
Isotone regression minimal lower sets algorithm convex cones dual convex cones projections

Citation

Dykstra, Richard L.; Robertson, Tim. An Algorithm for Isotonic Regression for Two or More Independent Variables. Ann. Statist. 10 (1982), no. 3, 708--716. doi:10.1214/aos/1176345866. https://projecteuclid.org/euclid.aos/1176345866


Export citation