Maharani, Retno Indah (2018) Metode Bootstrap Dalam Regresi Cox Proportional Hazard Untuk Laju Kesembuhan Pasien TBC DI RSI UNISMA Malang. Sarjana thesis, Universitas Brawijaya.
Abstract
Analysis of survival (survival) is an analysis of the data obtained from the length of time achieved an object until the occurrence of a particular event (failure event). One of the survival analysis that can be used is Cox regression. Although the baseline hazard is unknown, the Cox regression model can still provide information on hazard ratios (HR). In this study using a small sample size of medical record data inpatients of TBC disease in RSI UNISMA Malang in April to November 2014, amounting to 23 patients. To handle data with small sample sizes the bootstrap method will be applied in Cox proportional hazard regression. The objective is to know the application of bootstrap method in Cox proportional hazard regression and to know the factors that influence the rate of recovery of TB patient in RSI UNISMA Malang. The best model using the bootstrap method in Cox proportional hazard regression is obtained on the B = 100 loop. The factors that influence the rate of recovery of TB patients in RSI UNISMA Malang significantly based on the bootstrap confidence interval that does not contain zero are gender, status of history and employment status.
English Abstract
Analisis ketahanan hidup (survival) adalah analisis mengenai data yang diperoleh dari lama waktu yang dicapai suatu obyek sampai terjadinya peristiwa tertentu (failure event). Salah satu analisis survival yang dapat digunakan yaitu regresi Cox. Meski bentuk baseline hazard tidak diketahui, tetapi model regresi Cox tetap dapat memberikan informasi berupa hazard ratio (HR). Pada penelitian ini menggunakan ukuran sampel kecil yaitu data rekam medis pasien rawat inap penyakit TBC di RSI UNISMA Malang pada Bulan April hingga November 2014 yang berjumlah 23 pasien. Untuk menangani data dengan ukuran sampel kecil maka akan diterapkan metode bootstrap dalam regresi Cox proportional hazard. Tujuan yang ingin dicapai yaitu mengetahui penerapan metode bootstrap dalam regresi Cox proportional hazard dan mengetahui faktor-faktor yang mempengaruhi laju kesembuhan pasien penyakit TBC di RSI UNISMA Malang. Model terbaik menggunakan metode bootstrap dalam regresi Cox proportional hazard diperoleh pada pengulangan
| Item Type: | Thesis (Sarjana) |
|---|---|
| Identification Number: | SKR/MIPA/2018/108/051803513 |
| Uncontrolled Keywords: | Regresi Cox Proportional Hazard, Bootstrap, Interval Konfidensi Bootstrap, TBC. Cox Proportional Hazard Regression, Bootstrap, Bootstrap Confidence Interval, TBC. |
| Subjects: | 600 Technology (Applied sciences) > 616 Diseases > 616.9 Other disease > 616.99 Tumors and miscellaneous communicable diseases > 616.995 Tuberculosis |
| Divisions: | Fakultas Matematika dan Ilmu Pengetahuan Alam > Statistika |
| Depositing User: | Budi Wahyono Wahyono |
| Date Deposited: | 27 May 2020 16:46 |
| Last Modified: | 16 Oct 2021 04:07 |
| URI: | http://repository.ub.ac.id/id/eprint/168430 |
Preview |
Text
Retno Indah Maharani (2).pdf - Published Version Download (1MB) | Preview |
Actions (login required)
 |
View Item |