BAYES ESTIMATES FOR THE PARAMETERS OF POISSON TYPE LENGTH BIASED EXPONENTIAL CLASS MODEL USING NON-INFORMATIVE PRIORS

In this paper, the failure intensity has been characterized by one parameter length biased exponential class Software Reliability Growth Model (SRGM) considering the Poisson process of occurrence of software failures. This proposed length biased exponential class model is a function of parameters namely; total number of failures theta(0) and scale parameter theta(1). It is assumed that very little or no information is available about both these parameters. The Bayes estimators for parameters theta(0) and theta(1) have been obtained using non-informative priors for each parameter under square error loss function. The Monte Carlo simulation technique is used to study the performance of proposed Bayes estimators against their corresponding maximum likelihood estimators on the basis of risk efficiencies. It is concluded that both the proposed Bayes estimators of total number of failures and scale parameter perform well for proper choice of execution time.