Work

Optimal estimators in biadditive models and their families

Year: 2025

Type: article

Abstract: Biadditive regression models are linear models with an additive structure for their covariance matrix. We introduce commutative conditions and derive optimal estimators, namely Best Linear Unbiased Estimators (BLUE) and Best Quadratic Unbiased Estimators (BQUE). We develop a simulation study to compare the variance components estimates obtained through the proposed approach with those derived from Analysis of Variance and Markov Chain Monte Carlo methods. This research highlights that commutative orthogonal structures in these models are highly convenient to strengthen inference.

Source: Frontiers in Applied Mathematics and Statistics

DOI: 10.3389/fams.2025.1379210

Authors: Manuela Oliveira, Eugénio Garção, Armando Alexandre, Joana Paulino, João Mexia

Institutions: University of Évora, University of Lisbon, Universidade Nova de Lisboa

Language: English

Topic: Advanced Statistical Methods and Models

Subfield: Statistics and Probability

Field: Mathematics

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $1,418

Funders: Horizon 2020 Framework Programme, Fundação para a Ciência e a Tecnologia