ROBUST PARAMETER ESTIMATION FOR RANDOM EFFECT PANEL DATA MODEL IN THE PRESENCE OF HETEROSCEDASTICITY AND INFLUENTIAL OBSERVATIONS

2021 ◽  
Vol 4 (4) ◽  
pp. 561-569
Author(s):  
Sani Muhammad ◽  
Suleiman Shamsuddeen ◽  
Ismail G. Baoku
Keyword(s):  
Panel Data ◽  
Data Model ◽  
Random Effect ◽  
Estimation Method ◽  
Panel Data Model ◽  
Influential Observations ◽  
Weighting Method ◽  
Robust Parameter ◽  
Robust Parameter Estimation ◽  
Combine Problem

Panel data estimators can strongly be biased and inconsistent in the presence of heteroscedasticity and anomalous observations called influential observations (IOs) in Random effect (RE) panel data model. The existing methods (LWS, WLSF, WLSDRGP) address only the problem of IO but fail to remedy the combine problem of heteroscedasticity and IOs.  Therefore, in this research we develop a method that will remedy the combine problem of heteroscedasticity and IOs based on robust heteroscedasticity consistent covariance matrix (RHCCM) estimator and fast improvised influential distance (FIID) weighting method denoted by WLSFIID. The simulation and numerical evidences show that our proposed estimation method is more efficient than the existing methods by providing smallest bias, and smallest standard error of HC4 and HC5.

NONLINEAR PANEL DATA MODELS WITH DISTRIBUTION-FREE CORRELATED RANDOM EFFECTS

2021 ◽  
pp. 1-25
Author(s):  
Yu-Chin Hsu ◽  
Ji-Liang Shiu
Keyword(s):  
Panel Data ◽  
Data Model ◽  
Conditional Distribution ◽  
Unobserved Heterogeneity ◽  
Random Effect ◽  
Data Models ◽  
Panel Data Model ◽  
Panel Data Models ◽  
Likelihood Functions ◽  
Correlated Random Effects

Under a Mundlak-type correlated random effect (CRE) specification, we first show that the average likelihood of a parametric nonlinear panel data model is the convolution of the conditional distribution of the model and the distribution of the unobserved heterogeneity. Hence, the distribution of the unobserved heterogeneity can be recovered by means of a Fourier transformation without imposing a distributional assumption on the CRE specification. We subsequently construct a semiparametric family of average likelihood functions of observables by combining the conditional distribution of the model and the recovered distribution of the unobserved heterogeneity, and show that the parameters in the nonlinear panel data model and in the CRE specification are identifiable. Based on the identification result, we propose a sieve maximum likelihood estimator. Compared with the conventional parametric CRE approaches, the advantage of our method is that it is not subject to misspecification on the distribution of the CRE. Furthermore, we show that the average partial effects are identifiable and extend our results to dynamic nonlinear panel data models.

A panel data model of length of stay in hospitals for hip replacements

2021 ◽  
Vol 40 (7) ◽  
pp. 688-707
Author(s):  
Yan Meng ◽  
Jiti Gao ◽  
Xibin Zhang ◽  
Xueyan Zhao
Keyword(s):  
Panel Data ◽  
Length Of Stay ◽  
Data Model ◽  
Panel Data Model ◽  
Hip Replacements
Sign in / Sign up

Export Citation Format

Share Document