Nonparametric Bounds on the Income Distribution in the Presence of Item Nonresponse

R. Vazquez-Alvarez, B. Melenberg, A.H.O. van Soest

Research output: Working paperDiscussion paperOther research output

288 Downloads (Pure)

Abstract

Item nonresponse in micro surveys can lead to biased estimates of the parameters of interest if such nonresponse is nonrandom. Selection models can be used to correct for this, but parametric and semiparametric selection models require additional assumptions. Manski has recently developed a new approach, showing that, without additional assumptions, the parameters of interest are identified up to some bounding interval. In this paper, we apply Manski’s approach to estimate the distribution function and quantiles of personal income, conditional on given covariates, taking account of item nonresponse on income. Nonparametric techniques are used to estimate the bounding intervals. We consider worst case bounds, as well as bounds which are valid under nonparametric assumptions on monotonicity or under exclusion restrictions.
Original languageEnglish
Place of PublicationTilburg
PublisherEconometrics
Number of pages30
Volume1999-33
Publication statusPublished - 1999

Publication series

NameCentER Discussion Paper
Volume1999-33

Fingerprint

Item Nonresponse
Income Distribution
Selection Model
Estimate
Non-response
Interval
Semiparametric Model
Quantile
Biased
Monotonicity
Covariates
Distribution Function
Valid
Restriction

Keywords

  • nonparametrics
  • bounds and identification
  • sample non-response

Cite this

Vazquez-Alvarez, R., Melenberg, B., & van Soest, A. H. O. (1999). Nonparametric Bounds on the Income Distribution in the Presence of Item Nonresponse. (CentER Discussion Paper; Vol. 1999-33). Tilburg: Econometrics.
Vazquez-Alvarez, R. ; Melenberg, B. ; van Soest, A.H.O. / Nonparametric Bounds on the Income Distribution in the Presence of Item Nonresponse. Tilburg : Econometrics, 1999. (CentER Discussion Paper).
@techreport{d37fb6a5207542b2b0b451de7419ceb0,
title = "Nonparametric Bounds on the Income Distribution in the Presence of Item Nonresponse",
abstract = "Item nonresponse in micro surveys can lead to biased estimates of the parameters of interest if such nonresponse is nonrandom. Selection models can be used to correct for this, but parametric and semiparametric selection models require additional assumptions. Manski has recently developed a new approach, showing that, without additional assumptions, the parameters of interest are identified up to some bounding interval. In this paper, we apply Manski’s approach to estimate the distribution function and quantiles of personal income, conditional on given covariates, taking account of item nonresponse on income. Nonparametric techniques are used to estimate the bounding intervals. We consider worst case bounds, as well as bounds which are valid under nonparametric assumptions on monotonicity or under exclusion restrictions.",
keywords = "nonparametrics, bounds and identification, sample non-response",
author = "R. Vazquez-Alvarez and B. Melenberg and {van Soest}, A.H.O.",
note = "Pagination: 30",
year = "1999",
language = "English",
volume = "1999-33",
series = "CentER Discussion Paper",
publisher = "Econometrics",
type = "WorkingPaper",
institution = "Econometrics",

}

Vazquez-Alvarez, R, Melenberg, B & van Soest, AHO 1999 'Nonparametric Bounds on the Income Distribution in the Presence of Item Nonresponse' CentER Discussion Paper, vol. 1999-33, Econometrics, Tilburg.

Nonparametric Bounds on the Income Distribution in the Presence of Item Nonresponse. / Vazquez-Alvarez, R.; Melenberg, B.; van Soest, A.H.O.

Tilburg : Econometrics, 1999. (CentER Discussion Paper; Vol. 1999-33).

Research output: Working paperDiscussion paperOther research output

TY - UNPB

T1 - Nonparametric Bounds on the Income Distribution in the Presence of Item Nonresponse

AU - Vazquez-Alvarez, R.

AU - Melenberg, B.

AU - van Soest, A.H.O.

N1 - Pagination: 30

PY - 1999

Y1 - 1999

N2 - Item nonresponse in micro surveys can lead to biased estimates of the parameters of interest if such nonresponse is nonrandom. Selection models can be used to correct for this, but parametric and semiparametric selection models require additional assumptions. Manski has recently developed a new approach, showing that, without additional assumptions, the parameters of interest are identified up to some bounding interval. In this paper, we apply Manski’s approach to estimate the distribution function and quantiles of personal income, conditional on given covariates, taking account of item nonresponse on income. Nonparametric techniques are used to estimate the bounding intervals. We consider worst case bounds, as well as bounds which are valid under nonparametric assumptions on monotonicity or under exclusion restrictions.

AB - Item nonresponse in micro surveys can lead to biased estimates of the parameters of interest if such nonresponse is nonrandom. Selection models can be used to correct for this, but parametric and semiparametric selection models require additional assumptions. Manski has recently developed a new approach, showing that, without additional assumptions, the parameters of interest are identified up to some bounding interval. In this paper, we apply Manski’s approach to estimate the distribution function and quantiles of personal income, conditional on given covariates, taking account of item nonresponse on income. Nonparametric techniques are used to estimate the bounding intervals. We consider worst case bounds, as well as bounds which are valid under nonparametric assumptions on monotonicity or under exclusion restrictions.

KW - nonparametrics

KW - bounds and identification

KW - sample non-response

M3 - Discussion paper

VL - 1999-33

T3 - CentER Discussion Paper

BT - Nonparametric Bounds on the Income Distribution in the Presence of Item Nonresponse

PB - Econometrics

CY - Tilburg

ER -

Vazquez-Alvarez R, Melenberg B, van Soest AHO. Nonparametric Bounds on the Income Distribution in the Presence of Item Nonresponse. Tilburg: Econometrics. 1999. (CentER Discussion Paper).