Wahyuni, Ane (2019) Propensity Score Stratification (PSS) Menggunakan Multivariate Adaptive Regression Spline (MARS) pada Kasus Diabetes Melitus Tipe 2. Other thesis, Institut Teknologi Sepuluh Nopember.
Preview |
Text
06211745000005-Undergraduate_Theses.pdf - Published Version Download (1MB) | Preview |
Abstract
Diabetes Melitus (DM) merupakan penyakit gangguan metabolik menahun akibat pankreas tidak memproduksi cukup insulin atau tubuh tidak dapat menggunakan insulin yang diproduksi secara efektif. Berdasarkan laporan dari kementrian kesehatan, provinsi Jawa Timur memiliki angka prevalensi DM sebesar 2,1%. Angka ini lebih besar dari angka prevalensi di Indonesia yaitu 1,5%. Melihat tingginya kejadian DM di Jawa Timur, maka perlu dilakukan penelitian untuk mengetahui faktor-faktor penyebab terjadinya komplikasi DM. Faktor-faktor tersebut diduga memiliki hubungan antara satu dengan yang lainnya, sehingga perlu dilakukan analisis untuk mengurangi bias yang disebabkan oleh faktor confounding menggunakan Propensity Score Stratification (PSS). Metode yang digunakan untuk estimasi nilai propensity score adalah Multivariate Adaptive Regression Spline (MARS). Hasil analisis menunjukkan bahwa variabel yang terpilih sebagai confounding adalah aktivitas olahraga. Berdasarkan model MARS, diketahui bahwa variabel usia, jenis kelamin, riwayat genetik, lama menderita, obesitas, dan hipertensi memiliki pengaruh terhadap variabel atktivitas olahraga. Pada estimasi nilai ATE juga diketahui bahwa variabel aktivitas olahraga berpengaruh terhadap komplikasi penyakit DM. Sementara itu, besarnya bias yang dapat direduksi oleh metode PSS MARS adalah kurang dari 25%.
==============================================================================================================================
Diabetes Mellitus is a chronic metabolic disorder caused by the pancreas not producing enough insulin or the body cannot use insulin produced effectively. Based on reports from the Ministry of Health, East Java province has a DM prevalence rate of 2.1%. This figure is greater than the prevalence rate in Indonesia, which is 1.5%. Seeing the high incidence of DM in East Java, it is necessary to conduct research to know the factors that cause DM complications. These factors are thought to have a relationship between one another, so it is necessary to do an analysis to reduce the bias caused by the confounding factors using Propensity Score Stratification (PSS). The method that used to estimate the value of propensity score is Multivariate Adaptive Regression Spline (MARS). The results of the analysis is show that the variable chosen as confounding is sports activity. Based on MARS model, it is known that age, sex, genetic history, time suffering, obesity, and hypertension have influence on sports activity. In the estimation of ATE value, it is known that sports activity variable affects the complications of DM disease. Meanwhile, the magnitude of the bias that can be reduced by PSS MARS method is less than 25%.
| Item Type: | Thesis (Other) |
|---|---|
| Additional Information: | RSSt 519.536 Wah p-1 2019 |
| Uncontrolled Keywords: | Confounding, Diabetes Melitus, MARS, PSS |
| Subjects: | Q Science Q Science > QA Mathematics Q Science > QA Mathematics > QA278.2 Regression Analysis. Logistic regression Q Science > QA Mathematics > QA76.6 Computer programming. Q Science > QA Mathematics > QA278 Cluster Analysis. Multivariate analysis. Correspondence analysis (Statistics) |
| Divisions: | Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis |
| Depositing User: | Ane Wahyuni |
| Date Deposited: | 27 Dec 2022 01:53 |
| Last Modified: | 27 Dec 2022 01:53 |
| URI: | http://repository.its.ac.id/id/eprint/63412 |
Actions (login required)
 |
View Item |