KEY PERFORMANCE INDICATORS (KPI) DAN ANALISIS KORELASI DEPARTEMEN PERAWATAN DI PERUSAHAAN CONSUMER GOODS (STUDI KASUS: PT TIRTA INVESTAMA DAN PT MADUBARU)
| Main Authors: | , ASTRI L WIKANINGTYAS, , Andi R. Wijaya, S.T.,M.Sc.,Ph.D |
|---|---|
| Format: | Thesis NonPeerReviewed |
| Terbitan: |
[Yogyakarta] : Universitas Gadjah Mada
, 2014
|
| Subjects: | |
| Online Access: |
https://repository.ugm.ac.id/133296/ http://etd.ugm.ac.id/index.php?mod=penelitian_detail&sub=PenelitianDetail&act=view&typ=html&buku_id=73876 |
Daftar Isi:
- In this time, maintenance department is considered as a department that simply throwing money, but actually existence of this department is very supportive of production activities. Performance measurement needs to be done to be able to determine the quality of the performance of each department in the company so as to know the indicators that affect the company's production levels. The quality of the quantitative measurement of performance is necessary so that the results provided more objective. This study aims to determine the correlation between the performance of the department and the vision on the company's as a performance measurement and determine key performance indicators in the maintenance department of the appropriate treatment to achieve the vision and mission. The research was conducted through the analysis of the correlation measurement and effect link between indicators. The result of maintenance departmen KPI in the company of mineral water obtained from the PLS processing, that is indicators E1, E5, O1, O4, and O10. The indicator consists of the maintenance total cost, number of productions, number of production and maintenance workers, production man hours, and number of maintenance workers. KPI models between sugar and mineral water company is different. This is due to differences in organizational systems (private and non-private company) on each company. KPI model of non-private company using PCA also different with the PLS processing. This is because PCA only takes characteristics of several predictor variables without any explanation given the relationship of each of these variables. On the other hand, PLS is very good method to processing data with large number of variables so that the models is more robust, superior, and effective in dealing with multicolinearity than PCA.