ANALISIS SURVIVAL DISTRIBUSI EKSPONENSIAL DUA PARAMETER PADA KASUS KAPAL TENGGELAM DI INDONESIA DENGAN SENSOR TIPE-II

Abstrak

Survival analysis is a statistical method used to analyze data on the time until a certain event occurs. This study aims to model the time interval between ship sinking events in Indonesia and estimate the probability of such events occurring in the future. The method used is survival analysis with a two-parameter exponential distribution on type-II censored data. The data used is secondary data on the waiting time for ship sinking events in Indonesia during the period 2003–2018. The model suitability test using the Kolmogorov–Smirnov test shows that the data follows an exponential distribution. Parameter estimation was performed using the maximum likelihood method to obtain the location parameter (μ) and scale parameter (θ) values, as well as confidence intervals at the 95% and 99% confidence levels. The results showed that the estimated parameter points μ and θ were −2.58 and 36.61, respectively. The 95% confidence interval for the θ parameter was in the range of 20.66 to 62.55, while the 99% confidence interval was in the range of 17.93 to 77.60. Furthermore, the estimated survival function at 67 months showed that the probability of no ship sinking during that period was 12%.