Robust estimation of dynamic fixed-effects panel data models

M. Aquaro, P. Cizek

Research output: Contribution to journalArticleScientificpeer-review

Abstract

This paper extends an existing outlier-robust estimator of linear dynamic panel data models with fixed effects, which is based on the median ratio of two consecutive pairs of first-order differenced data. To improve its precision and robustness properties, a general procedure based on higher-order pairwise differences and their ratios is designed. The asymptotic distribution of this class of estimators is derived. Further, the breakdown point properties are obtained under contamination by independent additive outliers and by the patches of additive outliers, and are used to select the pairwise differences that do not compromise the robustness properties of the procedure. The proposed estimator is additionally compared with existing methods by means of Monte Carlo simulations.
Original languageEnglish
Pages (from-to)169-186
JournalStatistical Papers
Volume55
Issue number1
DOIs
Publication statusPublished - 2014

Fingerprint

Fixed Effects
Robust Estimation
Panel Data
Additive Outliers
Data Model
Pairwise
Robustness
Estimator
Breakdown Point
Robust Estimators
Contamination
Asymptotic distribution
Outlier
Patch
Consecutive
Monte Carlo Simulation
Higher Order
First-order
Robust estimation
Fixed effects

Cite this

@article{5d4b228a4cac4794985e24f9aa60cfa8,
title = "Robust estimation of dynamic fixed-effects panel data models",
abstract = "This paper extends an existing outlier-robust estimator of linear dynamic panel data models with fixed effects, which is based on the median ratio of two consecutive pairs of first-order differenced data. To improve its precision and robustness properties, a general procedure based on higher-order pairwise differences and their ratios is designed. The asymptotic distribution of this class of estimators is derived. Further, the breakdown point properties are obtained under contamination by independent additive outliers and by the patches of additive outliers, and are used to select the pairwise differences that do not compromise the robustness properties of the procedure. The proposed estimator is additionally compared with existing methods by means of Monte Carlo simulations.",
author = "M. Aquaro and P. Cizek",
year = "2014",
doi = "10.1007{\%}2fs00362-013-0545-7",
language = "English",
volume = "55",
pages = "169--186",
journal = "Statistical Papers",
issn = "0932-5026",
publisher = "Springer New York",
number = "1",

}

Robust estimation of dynamic fixed-effects panel data models. / Aquaro, M.; Cizek, P.

In: Statistical Papers, Vol. 55, No. 1, 2014, p. 169-186.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Robust estimation of dynamic fixed-effects panel data models

AU - Aquaro, M.

AU - Cizek, P.

PY - 2014

Y1 - 2014

N2 - This paper extends an existing outlier-robust estimator of linear dynamic panel data models with fixed effects, which is based on the median ratio of two consecutive pairs of first-order differenced data. To improve its precision and robustness properties, a general procedure based on higher-order pairwise differences and their ratios is designed. The asymptotic distribution of this class of estimators is derived. Further, the breakdown point properties are obtained under contamination by independent additive outliers and by the patches of additive outliers, and are used to select the pairwise differences that do not compromise the robustness properties of the procedure. The proposed estimator is additionally compared with existing methods by means of Monte Carlo simulations.

AB - This paper extends an existing outlier-robust estimator of linear dynamic panel data models with fixed effects, which is based on the median ratio of two consecutive pairs of first-order differenced data. To improve its precision and robustness properties, a general procedure based on higher-order pairwise differences and their ratios is designed. The asymptotic distribution of this class of estimators is derived. Further, the breakdown point properties are obtained under contamination by independent additive outliers and by the patches of additive outliers, and are used to select the pairwise differences that do not compromise the robustness properties of the procedure. The proposed estimator is additionally compared with existing methods by means of Monte Carlo simulations.

U2 - 10.1007%2fs00362-013-0545-7

DO - 10.1007%2fs00362-013-0545-7

M3 - Article

VL - 55

SP - 169

EP - 186

JO - Statistical Papers

JF - Statistical Papers

SN - 0932-5026

IS - 1

ER -