Strongly consistent nonparametric forecasting and regression for stationary ergodic sequences

Sidney Yakowitz, L. Györfi, John Kieffer, G. Morvai

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Let {(X i, Y i)} be a stationary ergodic time series with (X, Y) values in the product space R d ⊗ R. This study offers what is believed to be the first strongly consistent (with respect to pointwise, least-squares, and uniform distance) algorithm for inferring m(x) = E[ Y 0

Original languageEnglish
Pages (from-to)24-41
Number of pages18
JournalJournal of Multivariate Analysis
Volume71
Issue number1
Publication statusPublished - 1999

Fingerprint

Product Space
Least Squares
Forecasting
Time series
Regression
Least squares
Stationary time series

Keywords

  • Forecasting
  • Nonparametric estimation
  • Time-series regression
  • Universal prediction

ASJC Scopus subject areas

  • Statistics, Probability and Uncertainty
  • Numerical Analysis
  • Statistics and Probability

Cite this

Strongly consistent nonparametric forecasting and regression for stationary ergodic sequences. / Yakowitz, Sidney; Györfi, L.; Kieffer, John; Morvai, G.

In: Journal of Multivariate Analysis, Vol. 71, No. 1, 1999, p. 24-41.

Research output: Contribution to journalArticle

@article{e96160c3e0274a649c82584052640d8c,
title = "Strongly consistent nonparametric forecasting and regression for stationary ergodic sequences",
abstract = "Let {(X i, Y i)} be a stationary ergodic time series with (X, Y) values in the product space R d ⊗ R. This study offers what is believed to be the first strongly consistent (with respect to pointwise, least-squares, and uniform distance) algorithm for inferring m(x) = E[ Y 0",
keywords = "Forecasting, Nonparametric estimation, Time-series regression, Universal prediction",
author = "Sidney Yakowitz and L. Gy{\"o}rfi and John Kieffer and G. Morvai",
year = "1999",
language = "English",
volume = "71",
pages = "24--41",
journal = "Journal of Multivariate Analysis",
issn = "0047-259X",
publisher = "Academic Press Inc.",
number = "1",

}

TY - JOUR

T1 - Strongly consistent nonparametric forecasting and regression for stationary ergodic sequences

AU - Yakowitz, Sidney

AU - Györfi, L.

AU - Kieffer, John

AU - Morvai, G.

PY - 1999

Y1 - 1999

N2 - Let {(X i, Y i)} be a stationary ergodic time series with (X, Y) values in the product space R d ⊗ R. This study offers what is believed to be the first strongly consistent (with respect to pointwise, least-squares, and uniform distance) algorithm for inferring m(x) = E[ Y 0

AB - Let {(X i, Y i)} be a stationary ergodic time series with (X, Y) values in the product space R d ⊗ R. This study offers what is believed to be the first strongly consistent (with respect to pointwise, least-squares, and uniform distance) algorithm for inferring m(x) = E[ Y 0

KW - Forecasting

KW - Nonparametric estimation

KW - Time-series regression

KW - Universal prediction

UR - http://www.scopus.com/inward/record.url?scp=0002645342&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0002645342&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0002645342

VL - 71

SP - 24

EP - 41

JO - Journal of Multivariate Analysis

JF - Journal of Multivariate Analysis

SN - 0047-259X

IS - 1

ER -