Noudoostbeni, Ali and Kaur, Kiran and Jenatabadi, Hashem Salarzadeh (2018) A comparison of structural equation modeling approaches with DeLone & McLean's model: A case study of radio-frequency identification user satisfaction in Malaysian university libraries. Sustainability, 10 (7). p. 2532. ISSN 2071-1050, DOI https://doi.org/10.3390/su10072532.
Full text not available from this repository.Abstract
This paper focuses on the application of mathematical theories in the study of information system (IS) success factors. The main objective is to apply Delone and McLean's IS success model for radio-frequency identification (RFID) sustainability in Malaysian university libraries. Two approaches are applied to estimate user satisfaction, such as the Bayesian and maximum likelihood estimation approaches. In order to identify the best approach, four mathematical indices are used, namely root mean squared error, absolute error, mean absolute percentage error, and the coefficient of determination. The results reveal that Bayesian estimation provides good fit to the data, unlike the model with the maximum likelihood estimator. This study addresses the causes for this difference between the two approaches, as well as the potential merits and shortcomings of the maximum likelihood approach. The current study presents a novel and practical modeling and prediction concept for researchers and experts in the field of computer science.
Item Type: | Article |
---|---|
Funders: | University of Malaya project number BK043-2016 |
Uncontrolled Keywords: | Bayesian structural equation modeling; RFID; library user satisfaction |
Subjects: | Z Bibliography. Library Science. Information Resources |
Divisions: | Faculty of Computer Science & Information Technology > Department of Information Science Faculty of Science > Department of Science and Technology Studies |
Depositing User: | Ms. Juhaida Abd Rahim |
Date Deposited: | 30 Apr 2019 03:47 |
Last Modified: | 30 Apr 2019 03:47 |
URI: | http://eprints.um.edu.my/id/eprint/21103 |
Actions (login required)
View Item |