Robust estimation and moment selection in dynamic fixed-effects panel data models

Pavel Cizek, Michele Aquaro

Research output: Contribution to journalArticleScientificpeer-review

Abstract

Considering linear dynamic panel data models with fixed effects, existing outlier–robust estimators based on the median ratio of two consecutive pairs of first-differenced data are extended to higher-order differencing. The estimation procedure is thus based on many pairwise differences and their ratios and is designed to combine high precision and good robust properties. In particular, the proposed two-step GMM estimator based on the corresponding moment equations relies on an innovative weighting scheme reflecting both the variance and bias of those moment equations, where the bias is assumed to stem from data contamination. To estimate the bias, the influence function is derived and evaluated. The robust properties of the estimator are characterized both under contamination by independent additive outliers and the patches of additive outliers. The proposed estimator is additionally compared with existing methods by means of Monte Carlo simulations.
LanguageEnglish
Pages675–708
JournalComputational Statistics
Volume33
Issue number2
DOIs
StatePublished - Jun 2018

Fingerprint

Fixed Effects
Robust Estimation
Panel Data
Additive Outliers
Data Model
Data structures
Moment Equations
Contamination
Moment
Estimator
Influence Function
Robust Estimators
Outlier
Weighting
Patch
Consecutive
Pairwise
Monte Carlo Simulation
Higher Order
Estimate

Keywords

  • dynamic panel data
  • generalized method of moments
  • influence function
  • pariwise differences

Cite this

@article{faecfdf70aaf4659a9b6df9571be7a77,
title = "Robust estimation and moment selection in dynamic fixed-effects panel data models",
abstract = "Considering linear dynamic panel data models with fixed effects, existing outlier–robust estimators based on the median ratio of two consecutive pairs of first-differenced data are extended to higher-order differencing. The estimation procedure is thus based on many pairwise differences and their ratios and is designed to combine high precision and good robust properties. In particular, the proposed two-step GMM estimator based on the corresponding moment equations relies on an innovative weighting scheme reflecting both the variance and bias of those moment equations, where the bias is assumed to stem from data contamination. To estimate the bias, the influence function is derived and evaluated. The robust properties of the estimator are characterized both under contamination by independent additive outliers and the patches of additive outliers. The proposed estimator is additionally compared with existing methods by means of Monte Carlo simulations.",
keywords = "dynamic panel data, generalized method of moments, influence function, pariwise differences",
author = "Pavel Cizek and Michele Aquaro",
year = "2018",
month = "6",
doi = "10.1007/s00180-017-0782-7",
language = "English",
volume = "33",
pages = "675–708",
journal = "Computational Statistics",
issn = "0943-4062",
publisher = "Springer Verlag",
number = "2",

}

Robust estimation and moment selection in dynamic fixed-effects panel data models. / Cizek, Pavel; Aquaro, Michele.

In: Computational Statistics, Vol. 33, No. 2, 06.2018, p. 675–708.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Robust estimation and moment selection in dynamic fixed-effects panel data models

AU - Cizek,Pavel

AU - Aquaro,Michele

PY - 2018/6

Y1 - 2018/6

N2 - Considering linear dynamic panel data models with fixed effects, existing outlier–robust estimators based on the median ratio of two consecutive pairs of first-differenced data are extended to higher-order differencing. The estimation procedure is thus based on many pairwise differences and their ratios and is designed to combine high precision and good robust properties. In particular, the proposed two-step GMM estimator based on the corresponding moment equations relies on an innovative weighting scheme reflecting both the variance and bias of those moment equations, where the bias is assumed to stem from data contamination. To estimate the bias, the influence function is derived and evaluated. The robust properties of the estimator are characterized both under contamination by independent additive outliers and the patches of additive outliers. The proposed estimator is additionally compared with existing methods by means of Monte Carlo simulations.

AB - Considering linear dynamic panel data models with fixed effects, existing outlier–robust estimators based on the median ratio of two consecutive pairs of first-differenced data are extended to higher-order differencing. The estimation procedure is thus based on many pairwise differences and their ratios and is designed to combine high precision and good robust properties. In particular, the proposed two-step GMM estimator based on the corresponding moment equations relies on an innovative weighting scheme reflecting both the variance and bias of those moment equations, where the bias is assumed to stem from data contamination. To estimate the bias, the influence function is derived and evaluated. The robust properties of the estimator are characterized both under contamination by independent additive outliers and the patches of additive outliers. The proposed estimator is additionally compared with existing methods by means of Monte Carlo simulations.

KW - dynamic panel data

KW - generalized method of moments

KW - influence function

KW - pariwise differences

U2 - 10.1007/s00180-017-0782-7

DO - 10.1007/s00180-017-0782-7

M3 - Article

VL - 33

SP - 675

EP - 708

JO - Computational Statistics

T2 - Computational Statistics

JF - Computational Statistics

SN - 0943-4062

IS - 2

ER -