Binti Karomah* -  universitas surakarta, Indonesia

DOI : 10.24269/silogisme.v7i2.6112

Main component analysis can be used to facilitate agencies in making decisions in improving the services to be provided because with the main component analysis it can focus on only a few main components of the many variables that affect the level of public image. The research approach used is a quantitative approach with a descriptive method. This research was conducted at the Architecture Study Program at the University of Surakarta (UNSA), with primary data as a source of data which was conducted by distributing questionnaires to applicants in the Architecture Studies program at the University of Surakarta which contained 6 questions representing 6 specific variables. The data obtained from this study were analyzed using the principal component analysis method. With the principal component analysis method, two main components are formed, namely the first main component, the variable coefficient of X1 (relatively cheap tuition fees), X2 (There are afternoon classes or employee classes), X3 (Lecturers who are competent in their fields), X4 (Accreditation). ) respectively are 0.499, 0.456, 0.360 and 0.473 with variable scores/values X1, X2, X3, X4 are 0.702, 0.641, 0.506 and 0.665. These four variables are included in the internal components that form the image of the Surakarta University Architecture Study Program. The second main component, the coefficients of the variables X5 (complete supporting facilities) and X6 (strategic campus location) are -0.489 and 0.659 respectively and scores are -0.571 and 0.768, these two variables are included in the external components of the program image. Surakarta University Architecture Studies. The total diversity of image-forming of the Surakarta University Architecture Study Program on the internal component is 32.98% and the external component is 22.62%, so it is known that the internal component is the most dominant component and has more influence on the image-forming of the Surakarta University Architecture Study Program than the external component


Principal Component Analysis, Correlation Matrix, Image
  1. Chatfield, C and Collins.(2000) Introductin To Multivariate Analisys. New
  2. York: Chapman dan Hall.
  3. Dudewicz, Edward. (1995) Statistika Matematika Modern. Bandung:
  4. Institut Teknologi Bandung.
  5. Draper, Norman dan Smith, Harry. (1992) . Analisis Regresi Terapan.
  6. Jakarta: Gramedia Pustaka Utama.
  7. Gaspers, Vincent.(1995). Teknik Analisis Dalam Penelitian Percobaan.
  8. Bandung: Tarsito.
  9. Iriawan, Nur dan Puji Astuti.(2006). Mengolah Data Statistik Dengan
  10. Mudah Menggunakan Minitab 14. New York: Chapman dan Hall.
  11. Koller, Philip. (2022). Manajemen Pemasaran jilid 2. Jakarta: Prenhallindo.
  12. Mardainis, Junadhi, M. Jamaris.2019. Analisa Faktor Principal
  13. Component Analysis dan Common Factor Analysis untuk Menentukan
  14. Minat Calon Mahasiswa Masuk STMIK Amik Riau. Jurnal SATIN ( Sains
  15. dan Teknologi Informasi).
  16. Narbuko, Cholid dan Achnadi. (2003). Metodologi Penelitian. Jakarta:
  17. Bumi Aksara.
  18. Subhash. (1996). Applied To Multivariate Techniques. USA: Wiley and
  19. Sons
  20. Simamora, Bilson.(2004). Panduan Riset Perilaku Konsumen. Jakarta:
  21. Gramedia Pustaka Utama.
  22. Supranto.(2004). Analisis Multivariat Arti dan Interpretasi. Jakarta: Adi
  23. Mahasatya.

Full Text:
Article Info
Submitted: 2022-11-10
Published: 2022-12-31
Section: Artikel
Article Statistics: