![]() So we compare the efficiency of estimators that we use with ML estimators used by them. have used ML estimators using the EM algorithm to estimate unknown parameters of EG distribution. To the best of our knowledge, this is the first study to obtain LS, WLS, MPS, LM estimators in the context of parameter estimation for EG distribution family. Additionally, we have illustrated the performance of fitting two data sets into the EG distribution. It shouldīe noted that we have used different estimation methods from earlier studies. We then compare the efficiencies of these estimators via a simulation study for different sample sizes and parameter settings. In this study, our aim is to estimate the unknown parameters of EG distribution family by using Maximum Likelihood (ML) estimation with Expectation-Maximization (EM) algorithm and Least Squares (LS), Weighted Least Squares (WLS), Maximum Product of Spacings (MPS) and L-moments (LM) estimation methods. Similarly, conducted various studies on compound distributions. examined Complementary Exponential Geometric (CEG) distribution and its characteristics. studied Poisson-Exponential (PE) distribution and its properties. ![]() generalized EP with the help of a power parameter and investigated its properties. In the same way with EG, also proposed Exponential Poisson (EP) distribution which has decreasing failure rate (DFR). ![]() Firstly, the Exponential Geometric (EG) distribution proposed by became the focus point of various studies. In recent years, various compound distributions are proposed by using well known lifetime distributions. It is generally considered as time until death or failure. Survival analysis includes modeling the time until the occurrence of an event of interest. Keywords: Exponential geometric distribution Maximum likelihood Least squares Weighted least squares Maximum product of spacings I-moments Lifetime data analysisĪbbrevations:EG: Exponential Geometric EP: Exponential Poisson DFR: Decreasing Failure Rate PE: Poisson-Exponential CEG: Complementary Exponential Geometric ML: Maximum Likelihood EM: Expectation-Maximization LS: Least Squares WLS: Weighted Least Squares MPS: Maximum Product of Spacings LM: L-moments AIC: Akaike Information Criterion At the end of the study, two lifetime data sets such as coal mine data and medical data about occupational safety and duration hospitalization studies are illustrated for application. Then we compare the efficiency of these estimators via a simulation study for different sample sizes and parameter settings. In this paper, we use maximum likelihood and also least squares, weighted least squares, maximum product of spacings and l-moments methods to estimate the unknown parameters of exponential geometric distribution family. They have used maximum likelihood method with expectation-maximization algorithm to estimate unknown parameters. Exponential Geometric distribution, introduced by them, is a flexible distribution for modeling the lifetime data sets. This implies convergence in probability of $\Lambda_n$ to $\lambda$, which is equivalent to consistency.The new compound distributions which are started to be used with the study of Adamidis, et al. Is true which implies convergence almost everywhere. The probability density function of the exponential distribution is defined as
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |