Wibaningrum, Gayatri (2024) Statistik Uji Measurement Invariance Pada Academic Motivation Scale Menggunakan Second-Order Confirmatory Factor Analysis Dengan Evaluasi Kebaikan Model Dynamic Fit Index. Masters thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 6003222017_Master-Thesis.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
6003222017_Master-Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 April 2027. Download (2MB) | Request a copy |
Abstract
Pengujian properti psikometri merupakan tahapan penting untuk memastikan bahwa sebuah alat ukur psikologi layak digunakan. Pengujian yang dilakukan mencakup evaluasi sumber bukti validitas berdasarkan struktur internal. Second-Order Confirmatory Factor Analysis (SO-CFA) merupakan salah satu metode yang digunakan untuk menguji validitas struktur internal pada konstruk psikologis yang kompleks, contohnya adalah Motivasi Akademik. Pada proses pengambilan data primer yang banyak dilakukan pada penelitian di bidang Psikologi, peneliti tidak dapat mengasumsikan distribusi data yang diperoleh, sehingga data mungkin saja tidak berdistribusi normal. Oleh karena itu, penting untuk mengkaji penggunaan estimator yang tidak mewajibkan pemenuhan asumsi normalitas, salah satunya adalah Model Implied Instrumental Variables Two-Stage Least Squares (MIIV-2SLS). Tujuan dari penelitian ini adalah melakukan uji measurement invariance pada alat ukur Academic Motivation Scale (AMS) versi Bahasa Indonesia menggunakan estimator MIIV-2SLS dengan evaluasi kebaikan model menggunakan Dynamic Fit Index (DFI). Penelitian ini melibatkan 300 mahasiswa aktif dari Departemen Statistika ITS yang sedang atau pernah mengambil mata kuliah Pengantar Teori Peluang. Berdasarkan hasil SO-CFA dengan estimator MIIV-2SLS, diperoleh nilai model fit yang cukup memuaskan. Hasil uji measurement invariance menunjukkan bahwa pada pengelompokan berdasarkan jenis kelamin memiliki invariansi pengukuran yang kuat, sedangkan pengelompokan berdasarkan angkatan menunjukkan invariansi pengukuran yang lemah. Penggunaan DFI juga menunjukkan performa yang baik serta mampu mengakomodasi model yang kompleks pada penelitian ini, yaitu adanya penambahan variabel instrumental yang dibutuhkan oleh estimator MIIV-2SLS. Temuan ini mengindikasikan bahwa AMS versi Bahasa Indonesia valid digunakan pada konteks mahasiswa perguruan tinggi di Indonesia. Namun, perlu hati-hati dalam membandingkan scoring mahasiswa berdasarkan angkatannya.
===================================================================================================================================
Psychometric properties testing is an important step to ensure that a psychological measurement tool is suitable for use. The test includes evaluating the source of validity evidence based on internal structure. Second-Order Confirmatory Factor Analysis (SO-CFA) is one of the method used to test the internal structure validity of complex psychological constructs, such as Academic Motivation. In the process of collecting primary data which is often done in research in the field of Psychology, researchers cannot assume the distribution of the data obtained, thus the data may not be normally distributed. Therefore, it is important to choose an estimator that does not require to meet the normality assumption, one of the example is the Model Implied Instrumental Variables Two-Stage Least Squares (MIIV-2SLS) estimator. The purpose of this study is to conduct a measurement invariance test on the Indonesian version of the Academic Motivation Scale (AMS) measuring tool using the MIIV-2SLS estimator with an evaluation of the goodness of fit model using the Dynamic Fit Index (DFI). This study involved 300 active undergraduate students from the Department of Statistics, ITS who are currently or had taken the Introduction to Probability Theory course. The results of the SO-CFA analysis with the MIIV-2SLS estimator obtained a fairly satisfactory model fit value. The results of the measurement invariance test showed that the grouping based on gender had strong measurement invariance, while the grouping based on grade showed weak measurement invariance. The use of DFI also shows good performance and is able to accommodate complex models in this study, as this study using the addition of instrumental variables needed by the MIIV-2SLS estimator. These findings indicate that the Indonesian version of the AMS is valid for use in the context of university students in Indonesia. However, pre-caution is needed in terms of comparing student scoring values based on their class.
| Item Type: | Thesis (Masters) |
|---|---|
| Uncontrolled Keywords: | dynamic fit index, measurement invariance, motivasi akademik, second-order confirmatory factor analysis |
| Subjects: | B Philosophy. Psychology. Religion > BF Psychology H Social Sciences > HA Statistics H Social Sciences > HA Statistics > HA29 Theory and method of social science statistics H Social Sciences > HA Statistics > HA31.3 Regression. Correlation. Logistic regression analysis. H Social Sciences > HA Statistics > HA31.7 Estimation |
| Divisions: | Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49101-(S2) Master Thesis |
| Depositing User: | Gayatri Wibaningrum |
| Date Deposited: | 23 Jan 2025 08:49 |
| Last Modified: | 23 Jan 2025 08:49 |
| URI: | http://repository.its.ac.id/id/eprint/116770 |
Actions (login required)
 |
View Item |