WEIBULL DISTRIBUTION BASED ON EDUCATION PARTLY INTERVAL CENSORED DATA

Abstract

The work in this project is concerned with the applying of techniques for the assessment of survival analysis in data that include censored observations. Survival analysis has a lot of achievement in the medical, engineering, economic, education and other fields and it also known as failure time analysis. Partly Interval Censoring (PIC) is one of the techniques of the censoring that used in the survival analysis and it can help to treat many types of data especially the incomplete data. One of the most commonly lifetime distribution used in the reliability applications is Weibull distribution. In this project we use Weibull model based on modified education partly interval censored data as well as medical data and simulation data. Based on the medical data, we found that our model is comparable with Turnbull method. From the education data and simulation study for this particular case, we can conclude that our proposed distribution describes well the nature of the model as compared to the Turnbull method in terms of the value of scale and shape parameter estimates. Plots of survival distribution function against failure time are used to examine the predicted survival patterns for the two types of failures.