ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 1901.02398
86
29
v1v2 (latest)

Monotone Least Squares and Isotonic Quantiles

8 January 2019
Alexandre Mösching
L. Duembgen
ArXiv (abs)PDFHTML
Abstract

We consider bivariate observations (X1,Y1),…,(Xn,Yn)(X_1,Y_1), \ldots, (X_n,Y_n)(X1​,Y1​),…,(Xn​,Yn​) such that, conditional on the XiX_iXi​, the YiY_iYi​ are independent random variables with distribution functions FXiF_{X_i}FXi​​, where (Fx)x(F_x)_x(Fx​)x​ is an unknown family of distribution functions. Under the sole assumption that x↦Fxx \mapsto F_xx↦Fx​ is isotonic with respect to stochastic order, one can estimate (Fx)x(F_x)_x(Fx​)x​ in two ways: (i) For any fixed yyy one estimates the antitonic function x↦Fx(y)x \mapsto F_x(y)x↦Fx​(y) via nonparametric monotone least squares, replacing the responses YiY_iYi​ with the indicators 1[Yi≤y]1_{[Y_i \le y]}1[Yi​≤y]​. (ii) For any fixed β∈(0,1)\beta \in (0,1)β∈(0,1) one estimates the isotonic quantile function x↦Fx−1(β)x \mapsto F_x^{-1}(\beta)x↦Fx−1​(β) via a nonparametric version of regression quantiles. We show that these two approaches are closely related, with (i) being more flexible than (ii). Then, under mild regularity conditions, we establish rates of convergence for the resulting estimators F^x(y)\hat{F}_x(y)F^x​(y) and F^x−1(β)\hat{F}_x^{-1}(\beta)F^x−1​(β), uniformly over (x,y)(x,y)(x,y) and (x,β)(x,\beta)(x,β) in certain rectangles as well as uniformly in yyy or β\betaβ for a fixed xxx.

View on arXiv
Comments on this paper