Estimasi Effect Size Meta Measurement Model Dengan Pendekatan Generalized Method Of Moments (GMM)

Suprihanto, Hary (2021) Estimasi Effect Size Meta Measurement Model Dengan Pendekatan Generalized Method Of Moments (GMM). Masters thesis, Institut Teknologi Sepuluh Nopember.

Text 06211850012006-Master_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (1MB) | Request a copy

Abstract

Generalisasi hasil sebuah penelitian terhadap populasi seringkali tidak dapat dilakukan hanya dengan menggunakan satu hasil temuan saja, sehingga diperlukan sintesis dari beberapa hasil penelitian untuk memperoleh kesimpulan yang terintegrasi. Sintesis beberapa hasil penelitian melalui meta-analysis telah berkembang dalam studi Structural Equational Modeling (SEM), salah satunya adalah Confirmatory Factor Analysis (CFA). Di sisi yang lain, berkaitan dengan CFA, seringkali ditemukan perbedaan pengukuran sebuah variabel secara teori sehingga diperlukan analisis lanjutan untuk mengetahui ketepatan pengukuran variabel melalui Meta-CFA. Penelitian ini bertujuan untuk mendapatkan effect size melalui Meta-CFA pada faktor-faktor yang mengukur kinerja perusahaan. Data yang digunakan adalah data kinerja perusahaan daerah air minum (PDAM) di Pulau Jawa tahun 2010-2018. Perbedaan pengukuran variabel kinerja PDAM menurut BPPSPAM dan Kepmendagri selanjutnya dianalisis dengan menggunakan beberapa indikator yaitu keuangan, pelayanan, operasional, sumber daya manusia, dan administrasi. Metode estimasi yang digunakan untuk menduga effect size gabungan yaitu Generalized Method of Moments (GMM). Hasil analisis dengan program R menunjukkan bahwa model Meta-CFA menurut Kepmendagri lebih baik dalam mengukur variabel kinerja jika dibandingkan dengan model menurut BPPSPAM. Lebih lanjut pada model pengukuran kinerja menurut Kepmendagri disimpulkan bahwa selama periode 2010-2018 indikator keuangan dan operasional signifikan dalam mengukur kinerja PDAM di pulau Jawa.
============================================================================================
Generalization of the results of a study to the population often cannot be done using only one finding, so a synthesis of several research results is needed to obtain an integrated conclusion. Synthesis of several research results through meta-analysis has developed in the study of Structural Equational Modeling (SEM), one of which is Confirmatory Factor Analysis (CFA). On the other hand, with regard to CFA, there are often differences in the measurement of a variable in theory so that further analysis is needed to determine the accuracy of variable measurement through Meta-CFA. This study aims to obtain the effect size through Meta-CFA on the factors that measure company performance. The data used is the performance data of the regional drinking water companies (PDAM) in Java Island in 2010-2018. Differences in measurement of PDAM performance variables according to BPPSPAM and Kepmendagri are then analyzed using several indicators, namely finance, services, operations, human resources, and administration. The estimation method used to estimate the combined effect size is the Generalized Method of Moments (GMM). The results of the analysis with the R program show that the Meta-CFA model according to Kepmendagri is better at measuring performance variables when compared to the model according to BPPSPAM. Furthermore, in the performance measurement model according to Kepmendagri, during the period 2010-2018 it is concluded that financial and operational indicators are significant in measuring the performance of PDAMs in Java.

Item Type:	Thesis (Masters)
Uncontrolled Keywords:	Meta-CFA, Effect Size, GMM, Kinerja, Meta-CFA, Effect Size, GMM, Performance
Subjects:	Q Science > QA Mathematics > QA278.5 Principal components analysis. Factor analysis. Correspondence analysis (Statistics)
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49101-(S2) Master Thesis
Depositing User:	Hary Suprihanto
Date Deposited:	10 Mar 2021 03:56
Last Modified:	10 Mar 2021 03:56
URI:	http://repository.its.ac.id/id/eprint/84015

Actions (login required)

View Item