Título: Estimating Variance of Random Effects to Address Multiple Problems in Small Area Estimation
Ponente: Partha Lahiri (University of Maryland)
Fecha y hora: 31/10/2024, 12:00
Inscripción online (cierre 30 minutos antes del inicio): https://forms.gle/xt3Aq4XzYfa28ZPQ8
Lugar: Sala de Seminarios del Edificio Torretamarit (CIO) y online
Organizador: Domingo Morales González
Abstract:
For several decades, area-level models have played a critical role in the theory and practice of small area estimation. In this context, we propose a random effects variance estimator that simultaneously (i) improves the estimation of the related shrinkage factors, (ii) protects empirical best linear unbiased predictors (EBLUP) of the random effects from the common over-shrinkage problem, and (iii) avoids complex bias correction in generating strictly positive second-order unbiased mean square error (MSE) estimators, either through the Taylor series or a single parametric bootstrap method. The idea of achieving multiple desirable properties in an EBLUP method through a suitably devised random effects variance estimator is innovative and holds promise for providing robust inferences for random effects within the EBLUP framework. The proposed methodology is evaluated using a Monte Carlo simulation study and real data analysis.