METODE DIAGONALLY WEIGHTED LEAST SQUARE (DWLS) PADA STRUCTURAL EQUATION MODELLING UNTUK DATA ORDINAL: STUDI KASUS DARI PENGGUNA JASA KERETA API MAJAPAHIT MALANG – PASAR SENEN

*Isnayanti Isnayanti -  Departemen Matematika, Universitas Gadjah Mada, Indonesia
Abdurakhman Abdurakhman -  Departemen Matematika, Universitas Gadjah Mada, Indonesia
Received: 13 May 2019; Published: 24 Jul 2019.
Open Access Copyright (c) 2019 MEDIA STATISTIKA
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Citation Format:
Article Info
Section: Articles
Language: ID
Full Text:
Statistics: 150 126
Abstract

Structural Equation Modelling (SEM) is used to examine the relationship between complex variables to obtain a comprehensive picture of the overall model. The basic assumptions in SEM are continuous data types and multivariate normality distributed. But in some studies on social sciences, educational sciences, and medical sciences, the data used usually comes from ordinal variables in the form of a Likert scale which causes data to be not multivariate normal distribution. Diagonally Weighted Least Square (DWLS) is one method that can be used to overcome this problem. In this paper, ordinal data analysis will be conducted on SEM using polychoric correlation data with the DWLS method to compare the results of the suitability of the model with the Maximum Likelihood (ML) method. The discussion is complemented by a case study of the effect of service quality on customer satisfaction and loyalty of Majapahit Railway service in Malang-Pasar Senen.The results showed that the proposed model fit after modification model based on the criteria of 'goodness of fit' with chi-square value T=15.24, P-value=0.5785, RMSEA=0.000, GFI=0.99, AGFI=0.97, NNFI =1.03, CFI=1.00, PNFI=0.53.

Article Metrics: