Fetria, Putu Pavita Anindya (2026) Segmentasi Perilaku Hidup Bersih dan Sehat Mahasiswa FSAD ITS Menggunakan Kombinasi Structural Equation Modeling-Partial Least Squares (SEM-PLS) dan K-Means Clustering. Other thesis, Institut Teknologi Sepuluh Nopember.
|
Text
5003221148-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (4MB) | Request a copy |
Abstract
Perilaku Hidup Bersih dan Sehat (PHBS) merupakan aspek penting dalam menjaga kesehatan mahasiswa sebagai kelompok usia produktif, khususnya dalam upaya pencegahan Penyakit Tidak Menular (PTM). Aktivitas akademik yang padat dapat memengaruhi penerapan PHBS sehingga diperlukan identifikasi faktor-faktor yang berpengaruh serta karakteristik mahasiswa dalam membentuk perilaku tersebut. Penelitian ini bertujuan untuk menganalisis pengaruh faktor sosial, faktor ekonomi, dan pengetahuan kesehatan terhadap PHBS mahasiswa semester 2 Fakultas Sains dan Analitika Data ITS serta melakukan segmentasi mahasiswa berdasarkan karakteristik pembentukan PHBS. Data yang digunakan merupakan data primer yang diperoleh melalui penyebaran kuesioner kepada 282 mahasiswa FSAD ITS dengan teknik proportionate stratified random sampling. Metode yang digunakan adalah Structural Equation Modeling-Partial Least Squares (SEM-PLS) untuk menganalisis hubungan antar variabel laten dan K-Means Clustering berbasis residual untuk mengidentifikasi heterogenitas mahasiswa yang tidak teramati pada global model. Hasil analisis SEM-PLS menunjukkan bahwa faktor sosial, faktor ekonomi, dan pengetahuan kesehatan berpengaruh positif dan signifikan terhadap PHBS mahasiswa, dengan pengetahuan kesehatan sebagai faktor yang memiliki pengaruh terbesar. Global model menghasilkan nilai R^2 sebesar 54,4% yang menunjukkan kemampuan penjelasan model dalam kategori moderat. Hasil segmentasi menghasilkan dua kelompok mahasiswa, yaitu Segmen Pembentukan PHBS Kurang Terjelaskan oleh Model dan Segmen Pembentukan PHBS Terjelaskan oleh Model. Model SEM-PLS pada Segmen Pembentukan PHBS Terjelaskan oleh Model memiliki kemampuan penjelasan yang lebih baik dengan nilai R^2 sebesar 70%, lebih tinggi dibandingkan global model (R^2=54,4%) maupun Segmen Pembentukan PHBS Kurang Terjelaskan oleh Model (R^2=33,1%). Hasil penelitian menunjukkan bahwa kombinasi SEM-PLS dan K-Means Clustering mampu mengidentifikasi heterogenitas pola pembentukan PHBS mahasiswa sehingga dapat menjadi dasar dalam penyusunan strategi peningkatan PHBS yang lebih sesuai dengan karakteristik masing-masing kelompok mahasiswa.
====================================================================================================================================
Clean and Healthy Living Behavior (PHBS) is an important aspect in maintaining the health of students as a productive age group, especially in efforts to prevent Non-Communicable Diseases (NCDs). Busy academic activities can affect the implementation of PHBS so it is necessary to identify the influential factors and characteristics of students in forming this behavior. This study aims to analyze the influence of social factors, economic factors, and health knowledge on PHBS of second semester students of the Faculty of Science and Data Analytics ITS and to segment students based on the characteristics of PHBS formation. The data used are primary data obtained through distributing questionnaires to 282 FSAD ITS students class of 2025 using proportionate stratified random sampling technique. The method used is Structural Equation Modeling-Partial Least Squares (SEM-PLS) to analyze the relationship between latent variables and residual-based K-Means Clustering to identify student heterogeneity that is not observed in the global model. The results of the SEM-PLS analysis show that social factors, economic factors, and health knowledge have a positive and significant effect on student PHBS, with health knowledge as the factor that has the greatest influence. The global model produced R^2 value of 54.4%, indicating the model's explanatory power in the moderate category. The segmentation results produced two groups of students, namely the segment where PHBS formation is less explained by the model and the segment where PHBS formation is explained by the model. The SEM-PLS model for the segment where PHBS formation is explained by the model demonstrated superior explanatory power with an R^2 value of 70%, higher than the global model (R^2= 54.4%) and the segment where PHBS formation is less explained by the model (R^2= 33.1%). The results showed that the combination of SEM-PLS and K-Means Clustering was able to identify the heterogeneity of students' PHBS formation patterns so that it can be a basis for developing PHBS improvement strategies that are more appropriate to the characteristics of each student group.
| Item Type: | Thesis (Other) |
|---|---|
| Uncontrolled Keywords: | K-Means Clustering, Mahasiswa FSAD ITS, PHBS, Segmentasi, SEM-PLS, FSAD ITS Students, K-Means Clustering, PHBS, Segmentation, SEM-PLS |
| Subjects: | H Social Sciences > HA Statistics > HA29 Theory and method of social science statistics Q Science > QA Mathematics > QA278.3 Structural equation modeling. |
| Divisions: | Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis |
| Depositing User: | Putu Pavita Anindya Fetria |
| Date Deposited: | 29 Jul 2026 02:12 |
| Last Modified: | 29 Jul 2026 02:12 |
| URI: | http://repository.its.ac.id/id/eprint/139261 |
Actions (login required)
![]() |
View Item |
