Skripsi
MODEL REGRESI COX EXTENDED UNTUK PEMODELAN SURVIVAL TIME DENGAN METODE ESTIMASI PARAMETER BRESLOW PARTIAL LIKELIHOOD PADA DATA KAMBUH PASIEN ENDOMETRIOSIS
Extended Cox Model is one of modified models used to overcome non proportional hazard on Cox Proportional Hazard model. This research purpose is to estimate the parameter of Extended Cox Regression Model on ties data using Breslow method. Model applied to relapse data of 39 Endometriosis patiens with 8 independent variables which is take effect of Endometriosis relapse time. From the analysis with R.3.1.5 software, it is obtained that consumption of milk 5-7 times/week variable does not meet proportional hazard assumption and Extended Cox Model with g(t)=t function time is the best model. While the significant variables are milk consumption, cheese consumption, stay up late, and types of Endometriosis. Hazard ratio of milk consumption 5-7 times/week varies depending of the time. Consumption of milk 3-4 times/week has a risk of relapse 5,445 times greater compared to almost never consume milk. Stay up late 2 times/week has a risk of relapse 5,108 times greater compared to stay up late less than 1 time/week. Endometriosis patiens with Adenomiosis type has a risk 4,072 greater compared to spots Endometriosis and chocolate cyst types. While consumption of cheese 1-3 times/week has a risk 0,016 smaller compared to almost never consume cheese. Keywords : Breslow Method, Endometriosis, Extended Cox Model, Survival Analysis, ties
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2107003423 | T55564 | T555642021 | Central Library (Referens) | Available but not for loan - Not for Loan |
No other version available