Pseudo Empirical Best Prediction of Multiple Characteristics in Small Areas

2026-03-10

AI Summary

This study addresses the bias and inconsistency arising in multivariate small area mean estimation under complex sampling designs when the sampling mechanism is ignored. To resolve this, the authors propose a multivariate pseudo empirical best linear unbiased prediction (EBLUP) method that explicitly incorporates survey weights. Built upon a multivariate nested error regression model, the approach coherently integrates both unit-level and area-level data and employs a bootstrap procedure to estimate the prediction mean squared error. By innovatively embedding design weights into the multivariate small area estimation framework, the method ensures design consistency and high estimation accuracy. Simulation studies demonstrate its favorable statistical properties, and an application to real housing data further confirms its effectiveness and practical utility.

Technology Category

• Machine Learning: Ensemble Methods
• Intelligent Robots: State Estimation
• Multiagent Systems: Mechanism Design

Application Category

• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems

Abstract

Small area estimators that ignore the sampling design lack design consistency when the sampling mechanism is complex and may be severely biased under informative designs. Existing procedures that account for the survey weights under unit-level models typically focus on a single response variable. This paper addresses the estimation of area means for several dependent target variables under a multivariate nested error regression (MNER) model. We propose a multivariate pseudo-empirical best linear unbiased predictor that accounts for the sampling mechanism. Moreover, by aggregating the MNER model, we derive a unified predictor that can be obtained from either unit-level or area-level data. Bootstrap procedures are proposed to estimate the mean squared errors (MSEs) of the proposed predictors. Simulation experiments are conducted to examine the properties of the proposed small area estimators and the MSE estimators. Finally, an application with housing data illustrates the proposed methods.

Problem

• small area estimation
• multivariate estimation
• informative sampling
• survey weights
• dependent variables

Innovation

• multivariate small area estimation
• pseudo-empirical best prediction
• informative sampling design
• nested error regression model
• bootstrap MSE estimation