Metode Linierisasi untuk Regresi Kuadrat Terkecil Parsial

Abstract

This research investigates Romeras local linearization approach as a variance pre- diction method in partial least squares (PLS) regression. By addressing limita- tions in the original PLS regression formula, the local linearization approach aims to improve accuracy and stability in variance predictions. Extensive simulations are conducted to assess the method’s performance, demonstrating its superiority over traditional algebraic methods and showcasing its computational advantages, particularly with a large number of predictors. Additionally, the study introduces a novel computational technique utilizing bootstrap parameters, enhancing compu- tational stability and robustness. Overall, the research provides valuable insights into the local linearization approach’s effectiveness, guiding researchers and prac- titioners in selecting more reliable and efficient regression modeling techniques.