Pemodelan Case Fatality Rate (CFR) akibat Demam Berdarah Dengue (DBD) Menggunakan Regresi Nonparametrik Spline Truncated di Jawa Barat

Adiya, Gannisa Sekar (2023) Pemodelan Case Fatality Rate (CFR) akibat Demam Berdarah Dengue (DBD) Menggunakan Regresi Nonparametrik Spline Truncated di Jawa Barat. Other thesis, Institut Teknologi Sepuluh Nopember.

[thumbnail of 06211940000040-Undergraduate_Thesis.pdf] Text
06211940000040-Undergraduate_Thesis.pdf - Accepted Version
Restricted to Repository staff only until 1 October 2025.

Download (1MB) | Request a copy

Abstract

Demam Berdarah Dengue (DBD) merupakan penyakit menular yang dapat menyebabkan kematian dalam kurun waktu yang relatif singkat. Tingkat terjangkitnya penyakit DBD di Indonesia merupakan yang tertinggi di antara negara-negara Asia Tenggara. Penyakit ini telah membawa banyak korban jiwa. Dari tahun ke tahun, jumlah kasus dan kematian akibat DBD mengalami peningkatan. Salah satu indikator yang digunakan dalam mengendalikan penyakit DBD adalah Case Fatality Rate (CFR). CFR merupakan proporsi kematian terhadap keseluruhan kasus DBD. Provinsi Jawa Barat merupakan provinsi terpadat di Indonesia dan DBD sangat endemik di provinsi ini. Pada tahun 2021, CFR akibat DBD di Provinsi Jawa Barat melebihi batas 0,70% yang telah ditetapkan pada Strategi Nasional (STRATNAS) Penanggulangan Dengue yakni sebesar 0,88%. Untuk menurunan nilai CFR akibat DBD, diperlukan evaluasi untuk mencegah dan mengurangi keparahan yang menyebabkan kematian akibat DBD. Salah satu langkah awal dalam mengevaluasi kasus DBD adalah dengan mengetahui faktor-faktor yang mempengaruhi CFR akibat DBD di Provinsi Jawa Barat menggunakan metode statistik. CFR akibat DBD dan faktor-faktor yang diduga mempengaruhinya bersumber dari publikasi Badan Pusat Statistik (BPS) dan Dinas Kesehatan Jawa Barat, dimana pola hubungannya tidak membentuk pola tertentu, sehingga pendekatan regresi nonparametrik Spline Truncated menjadi rekomendasi, karena metode ini mempunyai fleksibilitas tinggi dan mampu menyesuaikan terhadap karakteristik lokal suatu data. Model Spline Truncated terbaik diperoleh dengan menggunakan titik knot optimal berdasarkan nilai Generalized Cross Validation (GCV) terkecil. Berdasarkan hasil penelitian, terdapat tiga variabel prediktor dugaan yang berpengaruh terhadap CFR akibat DBD diantaranya kepadatan penduduk, persentase rumah tangga yang memiliki akses terhadap sanitasi layak, dan persentase rumah tangga berperilaku hidup bersih dan sehat, dengan model terbaik adalah kombinasi knot 3,3,3,2 dengan koefisien determinasi sebesar 87,80%.
===============================================================================================================================
Dengue fever is an infectious disease that can cause death in a relatively short period of time. The rate of dengue in Indonesia is the highest among Southeast Asian countries. This disease has taken many lives. From year to year, the number of cases and deaths due to DHF has increased. One of the indicators used in controlling DHF is the Case Fatality Rate (CFR). CFR is the proportion of deaths to all DHF cases. West Java Province is the most populous province in Indonesia and DHF is highly endemic in this province. In 2021, the CFR due to DHF in West Java Province exceeded the 0,70% limit set in the National Strategy for Dengue Management, which is 0,88%. To reduce the CFR value due to DHF, an evaluation is needed to prevent and reduce the severity that causes death from DHF. One of the first steps in evaluating DHF cases is to determine the factors that influence the CFR due to DHF in West Java Province using statistical methods. CFR due to DHF and the factors that allegedly affect it are sourced from the publication of the Central Bureau of Statistics and the West Java Health Office, where the relationship pattern does not form a certain pattern, so the Spline Truncated nonparametric regression approach is recommended, because this method has high flexibility and is able to adjust to the local characteristics of a data. The best Spline Truncated model is obtained by using optimal knot points based on the smallest Generalized Cross Validation (GCV) value. Based on the results of the study, there are three predictor variables suspected to have an effect on CFR due to DHF including population density, percentage of households that have access to proper sanitation, and percentage of households with clean and healthy living behaviors, with the best model being a combination of 3,3,3,2 knots with a coefficient of determination of 87,80%.

Item Type: Thesis (Other)
Uncontrolled Keywords: CFR, DBD, DHF, Nonparametric, Nonparametrik, Spline Truncated
Subjects: Q Science > QA Mathematics > QA278.2 Regression Analysis. Logistic regression
Divisions: Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis
Depositing User: Gannisa Sekar Adiya
Date Deposited: 06 Sep 2023 03:07
Last Modified: 06 Sep 2023 03:07
URI: http://repository.its.ac.id/id/eprint/104309

Actions (login required)

View Item View Item