Expectation-Maximization Algorithm Estimation Method in Automated Model Selection Procedure for Seemingly Unrelated Regression Equations Models

Model selection is the process of choosing a model from set possible models. The model's ability to generalise means it can fit both current and future data. Despite numerous emergences procedures in selecting models automatically, there has been lack studies on multiple equations models, particularly seemingly unrelated regression (SURE) Hence, this study concentrates an automated procedure for SURE by integrating expectation-maximization (EM) algorithm estimation method, named SURE(EM)-Autometrics. This extension was originally initiated Autometrics, which only applicable single equation. To assess performance SURE(EM)-Autometrics, simulation analysis conducted under two strengths correlation among levels significance two-equation with up 18 variables initial general unrestricted (GUM). Three econometric have utilised as testbed true specification search. results were divided into four categories where tight level 1% had contributed high percentage all containing precisely comparable specifications. Then, empirical comparison techniques using water quality index (WQI) System select simultaneously proved be more efficient than equation selection. SURE(EM)-Autometrics dominated being at top rankings most error measures. integration EM appropriate improving