Nonparametric two-step regression estimation when regressors and error are dependent

Research output: Contribution to journalArticle

24 Citations (Scopus)

Abstract

This paper considers estimation of the function g in the model Yt = g(Xt) + εt when E(εt|Xt) ≠ 0 with nonzero probability. We assume the existence of an instrumental variable Zt that is independent of εt, and of an innovation ηt = Xt - E(Xt|Zt). We use a nonparametric regression of Xt on Zt to obtain residuals η̂t, which in turn are used to obtain a consistent estimator of g. The estimator was first analyzed by Newey, Powell & Vella (1999) under the assumption that the observations are independent and identically distributed. Here we derive a sample mean-squared-error convergence result for independent identically distributed observations as well as a uniform-convergence result under time-series dependence.

Original languageEnglish (US)
Pages (from-to)289-300
Number of pages12
JournalCanadian Journal of Statistics
Volume28
Issue number2
DOIs
StatePublished - Jun 2000

Fingerprint

Regression Estimation
Identically distributed
Convergence Results
Dependent
Instrumental Variables
Consistent Estimator
Sample mean
G-function
Nonparametric Regression
Uniform convergence
Mean Squared Error
Time series
Estimator
Observation
Model

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

@article{944d9e3cbcd74067a06d2978521bae51,
title = "Nonparametric two-step regression estimation when regressors and error are dependent",
abstract = "This paper considers estimation of the function g in the model Yt = g(Xt) + εt when E(εt|Xt) ≠ 0 with nonzero probability. We assume the existence of an instrumental variable Zt that is independent of εt, and of an innovation ηt = Xt - E(Xt|Zt). We use a nonparametric regression of Xt on Zt to obtain residuals η̂t, which in turn are used to obtain a consistent estimator of g. The estimator was first analyzed by Newey, Powell & Vella (1999) under the assumption that the observations are independent and identically distributed. Here we derive a sample mean-squared-error convergence result for independent identically distributed observations as well as a uniform-convergence result under time-series dependence.",
author = "Joris Pinkse",
year = "2000",
month = "6",
doi = "10.2307/3315979",
language = "English (US)",
volume = "28",
pages = "289--300",
journal = "Canadian Journal of Statistics",
issn = "0319-5724",
publisher = "Statistical Society of Canada",
number = "2",

}

Nonparametric two-step regression estimation when regressors and error are dependent. / Pinkse, Joris.

In: Canadian Journal of Statistics, Vol. 28, No. 2, 06.2000, p. 289-300.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Nonparametric two-step regression estimation when regressors and error are dependent

AU - Pinkse, Joris

PY - 2000/6

Y1 - 2000/6

N2 - This paper considers estimation of the function g in the model Yt = g(Xt) + εt when E(εt|Xt) ≠ 0 with nonzero probability. We assume the existence of an instrumental variable Zt that is independent of εt, and of an innovation ηt = Xt - E(Xt|Zt). We use a nonparametric regression of Xt on Zt to obtain residuals η̂t, which in turn are used to obtain a consistent estimator of g. The estimator was first analyzed by Newey, Powell & Vella (1999) under the assumption that the observations are independent and identically distributed. Here we derive a sample mean-squared-error convergence result for independent identically distributed observations as well as a uniform-convergence result under time-series dependence.

AB - This paper considers estimation of the function g in the model Yt = g(Xt) + εt when E(εt|Xt) ≠ 0 with nonzero probability. We assume the existence of an instrumental variable Zt that is independent of εt, and of an innovation ηt = Xt - E(Xt|Zt). We use a nonparametric regression of Xt on Zt to obtain residuals η̂t, which in turn are used to obtain a consistent estimator of g. The estimator was first analyzed by Newey, Powell & Vella (1999) under the assumption that the observations are independent and identically distributed. Here we derive a sample mean-squared-error convergence result for independent identically distributed observations as well as a uniform-convergence result under time-series dependence.

UR - http://www.scopus.com/inward/record.url?scp=0034343738&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034343738&partnerID=8YFLogxK

U2 - 10.2307/3315979

DO - 10.2307/3315979

M3 - Article

AN - SCOPUS:0034343738

VL - 28

SP - 289

EP - 300

JO - Canadian Journal of Statistics

JF - Canadian Journal of Statistics

SN - 0319-5724

IS - 2

ER -