Structural equation modeling of student satisfaction on lecturer's performance using diagonally weighted least square estimation

Closed

A. Melinda, E. Setiawan, K. Nisa, N. Herawati, S. Saidi, R.A. Yudanegara

2024 AIP Conference Proceedings Vol. 2970 Issue 1 Conference paper Cited by 0 Quartile

Abstract

Structural Equation Modeling (SEM) is a multivariate statistical technique that is able to analyze pattern of linear relationship between latent variables and their indicators. In general, there are several estimation methods in SEM, in this study the Diagonally Weighted Least Square (DWLS) estimation method in used. DWLS estimator is an unbiased and complete statistics. The aim of this research is to estimate the structural equation model of student Satisfaction of University of Lampung on the performance of lecturers in the lecture process and analyze the total effects between latent variables based on a questionnaire survey data. The model consists of three latent variables and sixteen indicator variables with a sample size of 500. The results of SEM analysis on the data show that the performance of the lecturers affects student satisfaction through intermediate variables that is quality of lectures with a total effect of 0.8564. Some goodness of fit tests were examined, i.e. Chi-Square of 352.45, Non Central Parameter of 251.45, Goodness of Fit Index of 0.98, Root Mean Square Error of Approximation of 0.71, Adjusted Goodness of Fit Index of 0.98 and Parsimonious Goodness of Fit Index of 0.73. These values show that the model fits to the data. © 2024 Author(s).

Affiliations

Department of Mathematics, Faculty of Mathematics and Natural Sciences, Universitas Lampung, Jl. Sumantri Brojonegoro no 1, Lampung, Bandar Lampung, 35141, Indonesia; Department of Geomatics Engineering, Institut Teknologi Sumatera, Jl. Terusan Ryacudu, Way Huwi, Jati Agung, Lampung Selatan, Lampung, 35365, Indonesia