Generalized and optimal sequence of weights on a progressive‐iterative approximation method with memory for least square fitting

Channark, Saknarin; Martínez-Moreno, Juan; Chaipunya, Parin; Jirakitpuwapat, Wachirapong

doi:10.1002/mma.8434

Cited by 1 publication

(1 citation statement)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In GLS, factors are derived by minimizing the weighted sum of squared discrepancies between the observed and estimated correlation matrices. This method is more efficient than the ULS under multivariate normality and is used when specific weighting of discrepancies is desired (31).…”

Section: Generalized Least Squares (Gls)mentioning

confidence: 99%

Guidelines for Applying Psychometrics in Sports Science: Transitioning from Traditional Methods to the AI Era

Guelmami,

Ben Aissa,

Ammar

et al. 2023

TJSSM

View full text Add to dashboard Cite

Background: The transition from conventional methods to the AI era in sports science emphasizes a critical need for comprehensive guidance in effectively applying psychometrics. This imperative is highlighted by dynamic transformations, where the integration of structured guidelines becomes indispensable for adeptly navigating the challenges and seizing the opportunities presented by advancing technologies. Aim: The aim of this study was to methodically outline and enhance the application of psychometrics in sports science, focusing on the transition from traditional methods to the artificial intelligence era. It sought to provide a clear, objective-driven framework for effectively utilizing psychometrics, particularly emphasizing integration with artificial intelligence technologies. Methods: The research employed a dual-pronged approach, developing theoretical frameworks and practical considerations. It outlined key principles for selecting and implementing psychometric tools, prioritizing reliability and validity. Additionally, the study closely examined ethical considerations linked to AI-driven psychometrics in sports, focusing on areas like privacy, potential bias, and the importance of maintaining transparency in these practices. Results: The study provided guidelines that bridged traditional psychometrics with emerging AI technologies in sports science. The results offered a roadmap for researchers, coaches, and practitioners, facilitating the transition to more robust assessment methodologies. Emphasis on data analysis and ethical considerations ensured responsible and effective integration of psychometrics and AI for athlete evaluation and development. Conclusion: This research offers a comprehensive framework for navigating the intersection of psychometrics and AI in sports science. Addressing both theoretical and practical aspects, the guidelines empower stakeholders to transition responsibly to advanced assessment methodologies in the evolving technological landscape.

show abstract

Section: Generalized Least Squares (Gls)mentioning

confidence: 99%