Distribution-free properties of isotonic regression

DOI10.1214/19-EJS1594MaRDI QIDQ2326057zbMATH OpenOpenAlexFDO

Authors Jake A. Soloff, Adityanand Guntuboyina, Jim Pitman

Publication date 4 October 2019

Published in Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1812.04249, https://projecteuclid.org/euclid.ejs/1569290688

zbMATH Keywords

fluctuation theoryconvex minorantstatistical dimensionquantiles of stochastic processesshape-constrained regression

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Order statistics; empirical distribution functions (62G30)

Abstract: It is well known that the isotonic least squares estimator is characterized as the derivative of the greatest convex minorant of a random walk. Provided the walk has exchangeable increments, we prove that the slopes of the greatest convex minorant are distributed as order statistics of the running averages. This result implies an exact non-asymptotic formula for the squared error risk of least squares in isotonic regression when the true sequence is constant that holds for every exchangeable error distribution.

Recommendations

• A general asymptotic scheme for inference under order restrictions
• Isotonic estimators of monotone densities and distribution functions: basic facts
• Risk bounds in isotonic regression
• The asymptotic distribution of the isotonic regression estimator over a general countable pre-ordered set
• scientific article; zbMATH DE number 1509414

Cites work

• scientific article; zbMATH DE number 1713116 (Why is no real title available?)
• scientific article; zbMATH DE number 3125737 (Why is no real title available?)
• scientific article; zbMATH DE number 193111 (Why is no real title available?)
• scientific article; zbMATH DE number 3441150 (Why is no real title available?)
• scientific article; zbMATH DE number 936413 (Why is no real title available?)
• scientific article; zbMATH DE number 3390139 (Why is no real title available?)
• Asymptotic behavior of the grenander estimator at density flat regions
• Convex minorants of random walks and Lévy processes
• Estimation of a convex function: Characterizations and asymptotic theory.
• Living on the edge: phase transitions in convex programs with random data
• Marginal densities of the least concave majorant of Brownian motion.
• Nonparametric shape-restricted regression
• On the quantiles of Brownian motion and their hitting times
• On the risk of convex-constrained least squares estimators under misspecification
• Projections onto order simplexes
• Risk bounds in isotonic regression
• Sharp MSE bounds for proximal denoising
• Sharp oracle inequalities for least squares estimators in shape restricted regression
• The Circumference of a Convex Polygon

Cited in

(14)

• Local convergence rates of the nonparametric least squares estimator with applications to transfer learning
• Isotonic Distributional Regression
• Adaptation in multivariate log-concave density estimation
• Isotonic regression in general dimensions
• Markovian structure in the concave majorant of Brownian motion
• The bias of isotonic regression
• Monotone least squares and isotonic quantiles
• Sharp asymptotics for isotonic regression
• Non-Markovianity of 2 K - B and a degeneration
• Risk bounds in isotonic regression
• A general asymptotic scheme for inference under order restrictions
• The distribution of sizes of ordered level sets
• Stochastic reduction of loss in estimating normal means by isotonic regression
• The asymptotic distribution of the isotonic regression estimator over a general countable pre-ordered set

This page was built for publication: Distribution-free properties of isotonic regression

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2326057)