ESTIMASI PARAMETER MODEL REGRESI COX DENGAN METODE BRESLOW PARTIAL LIKELIHOOD PADA DATA WAKTU KAMBUH PASIEN ENDOMETRIOSIS

Time of occurrence or time of survival in the analysis of survival divided into 2 kinds of events that are time without ties and time of the incident with ties. Ties or joint events are the circumstances that there are two or more individuals who experience events at the same time. Cox Proportional Hazard models are used to handle some of the data that experience ties. This research uses the breslow partial likelihood method to determine the estimate of the model parameter cox. The best model determination will use the forward selection. This study aims to determine the factors that significantly affect the time of the recurrence of endometriosis patients after surgery. Endometriosis is a medical condition in women characterized by the growth of endometrial cells outside the uterine cavity. One of the factors affecting the etiology of endometrisis is food factor. Variable that has significant effect on the time of recurrence is the consumption of cheese, types of endometriosis, rest time as well as milk consumption. The more often consuming cheese causes the risk of prolonged recurrence is greater than 50.66%, the type of endometriosis spots have a time of 3 Kalu longer than other types of endometriosis. At the break time variable, the longer the rest period, the longer the time of the patient relapse, which is 67.26%. In variable consumption of milk, the more milk consumption, the quicker the time of the patient relapse, which is 25.69%.