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. 0710.2496
106
14

Regression estimation from an individual stable sequence

12 October 2007
G. Morvai
Sanjeev R. Kulkarni
A. Nobel
ArXivPDFHTML
Abstract

We consider univariate regression estimation from an individual (non-random) sequence (x1,y1),(x2,y2),...∈ℜ×ℜ(x_1,y_1),(x_2,y_2), ... \in \real \times \real(x1​,y1​),(x2​,y2​),...∈ℜ×ℜ, which is stable in the sense that for each interval A⊆ℜA \subseteq \realA⊆ℜ, (i) the limiting relative frequency of AAA under x1,x2,...x_1, x_2, ...x1​,x2​,... is governed by an unknown probability distribution μ\muμ, and (ii) the limiting average of those yiy_iyi​ with xi∈Ax_i \in Axi​∈A is governed by an unknown regression function m(⋅)m(\cdot)m(⋅). A computationally simple scheme for estimating m(⋅)m(\cdot)m(⋅) is exhibited, and is shown to be L2L_2L2​ consistent for stable sequences {(xi,yi)}\{(x_i,y_i)\}{(xi​,yi​)} such that {yi}\{y_i\}{yi​} is bounded and there is a known upper bound for the variation of m(⋅)m(\cdot)m(⋅) on intervals of the form (−i,i](-i,i](−i,i], i≥1i \geq 1i≥1. Complementing this positive result, it is shown that there is no consistent estimation scheme for the family of stable sequences whose regression functions have finite variation, even under the restriction that xi∈[0,1]x_i \in [0,1]xi​∈[0,1] and yiy_iyi​ is binary-valued.

View on arXiv
Comments on this paper