Home > Research > Publications & Outputs > Data Masking by Noise Addition and the Estimati...
View graph of relations

Data Masking by Noise Addition and the Estimation of Nonlinear Regression Models

Research output: Contribution to journalJournal article

Published

Standard

Data Masking by Noise Addition and the Estimation of Nonlinear Regression Models. / Nolte (Lechner), Sandra; Pohlmeier, Winfried.

In: Jahrbuecher fuer Nationaloekonomie und Statistik, Vol. 225, No. 5, 01.10.2005, p. 517-528.

Research output: Contribution to journalJournal article

Harvard

Nolte (Lechner), S & Pohlmeier, W 2005, 'Data Masking by Noise Addition and the Estimation of Nonlinear Regression Models', Jahrbuecher fuer Nationaloekonomie und Statistik, vol. 225, no. 5, pp. 517-528. https://doi.org/10.1515/jbnst-2005-0503

APA

Nolte (Lechner), S., & Pohlmeier, W. (2005). Data Masking by Noise Addition and the Estimation of Nonlinear Regression Models. Jahrbuecher fuer Nationaloekonomie und Statistik, 225(5), 517-528. https://doi.org/10.1515/jbnst-2005-0503

Vancouver

Nolte (Lechner) S, Pohlmeier W. Data Masking by Noise Addition and the Estimation of Nonlinear Regression Models. Jahrbuecher fuer Nationaloekonomie und Statistik. 2005 Oct 1;225(5):517-528. https://doi.org/10.1515/jbnst-2005-0503

Author

Nolte (Lechner), Sandra ; Pohlmeier, Winfried. / Data Masking by Noise Addition and the Estimation of Nonlinear Regression Models. In: Jahrbuecher fuer Nationaloekonomie und Statistik. 2005 ; Vol. 225, No. 5. pp. 517-528.

Bibtex

@article{45d9457c76674ad2af332a9d3abcbb2a,
title = "Data Masking by Noise Addition and the Estimation of Nonlinear Regression Models",
abstract = "Data collecting institutions use a large range of masking procedures in order to protect data against disclosure. Generally, a masking procedure can be regarded as a kind of data filter that transforms the true data generating process. Such a transformation severely affects the quality of the data and limits its use for empirical research. A popular masking procedure is noise addition, which leads to inconsistent estimates if the additional measurement errors are ignored.This paper investigates to what extent appropriate econometric techniques can obtain consistent estimates of the true data generating process for parametric and nonparametric models when data is masked by noise addition. We show how the reduction of the data quality can be minimized using the local polynomial Simulation-Extrapolation (SIMEX) estimator. Evidence is provided by a Monte-Carlo study and by an application to firm-level data, where we analyze the impact of innovative activity on employment.",
keywords = "Data masking, errors-in-variables, SIMEX, local polynomial regression",
author = "{Nolte (Lechner)}, Sandra and Winfried Pohlmeier",
year = "2005",
month = oct,
day = "1",
doi = "10.1515/jbnst-2005-0503",
language = "English",
volume = "225",
pages = "517--528",
journal = "Jahrbuecher fuer Nationaloekonomie und Statistik",
issn = "0021-4027",
publisher = "Walter de Gruyter GmbH",
number = "5",

}

RIS

TY - JOUR

T1 - Data Masking by Noise Addition and the Estimation of Nonlinear Regression Models

AU - Nolte (Lechner), Sandra

AU - Pohlmeier, Winfried

PY - 2005/10/1

Y1 - 2005/10/1

N2 - Data collecting institutions use a large range of masking procedures in order to protect data against disclosure. Generally, a masking procedure can be regarded as a kind of data filter that transforms the true data generating process. Such a transformation severely affects the quality of the data and limits its use for empirical research. A popular masking procedure is noise addition, which leads to inconsistent estimates if the additional measurement errors are ignored.This paper investigates to what extent appropriate econometric techniques can obtain consistent estimates of the true data generating process for parametric and nonparametric models when data is masked by noise addition. We show how the reduction of the data quality can be minimized using the local polynomial Simulation-Extrapolation (SIMEX) estimator. Evidence is provided by a Monte-Carlo study and by an application to firm-level data, where we analyze the impact of innovative activity on employment.

AB - Data collecting institutions use a large range of masking procedures in order to protect data against disclosure. Generally, a masking procedure can be regarded as a kind of data filter that transforms the true data generating process. Such a transformation severely affects the quality of the data and limits its use for empirical research. A popular masking procedure is noise addition, which leads to inconsistent estimates if the additional measurement errors are ignored.This paper investigates to what extent appropriate econometric techniques can obtain consistent estimates of the true data generating process for parametric and nonparametric models when data is masked by noise addition. We show how the reduction of the data quality can be minimized using the local polynomial Simulation-Extrapolation (SIMEX) estimator. Evidence is provided by a Monte-Carlo study and by an application to firm-level data, where we analyze the impact of innovative activity on employment.

KW - Data masking

KW - errors-in-variables

KW - SIMEX

KW - local polynomial regression

U2 - 10.1515/jbnst-2005-0503

DO - 10.1515/jbnst-2005-0503

M3 - Journal article

VL - 225

SP - 517

EP - 528

JO - Jahrbuecher fuer Nationaloekonomie und Statistik

JF - Jahrbuecher fuer Nationaloekonomie und Statistik

SN - 0021-4027

IS - 5

ER -