Time prediction of failure a type of lamps by using general composite hazard rate model

Indonesian Operations Research Association - International Conference on Operations Research 2017

Riaman^1 ; Lesmana, E.^1 ; Subartini, B.^1 ; Supian, S.^1

Departemen Matematika, FMIPA Unpad, Bandung

45363, Indonesia^1

关键词: Exponential distributions;    Exponential models;    Hazard rate model;    Model parameters;    Parametric modeling;    Predictive values;    Survival Function;    Time predictions;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/332/1/012041/pdf
DOI  :  10.1088/1757-899X/332/1/012041

来源: IOP

【 摘 要 】

This paper discusses the basic survival model estimates to obtain the average predictive value of lamp failure time. This estimate is for the parametric model, General Composite Hazard Level Model. The random time variable model used is the exponential distribution model, as the basis, which has a constant hazard function. In this case, we discuss an example of survival model estimation for a composite hazard function, using an exponential model as its basis. To estimate this model is done by estimating model parameters, through the construction of survival function and empirical cumulative function. The model obtained, will then be used to predict the average failure time of the model, for the type of lamp. By grouping the data into several intervals and the average value of failure at each interval, then calculate the average failure time of a model based on each interval, the p value obtained from the tes result is 0.3296.