A COMPARISON OF THE PERFORMANCE OF THE GEOMETRIC PROCESS AND ITS EXTENSIONS

The geometric process (GP) is a stochastic that was an extension of the renewal process. It introduced by Lam (1988) in 1988 with intention to model failure repairable system whose times between failures become shorter and after repairs repair longer longer. GP has been widely studied literature reliability maintenance applied optimisation policies. Some authors have proposed various versions its extensions (or GP-like models), including α-series process, threshold GP, extended Poisson doubly doubly-ratio GP. papers also compare performance other models, but not This paper therefore reviews compares terms Akaike information criterion (AIC), corrected AIC (AICc) maximum likelihood (ML) based on 25 real-world datasets. Besides, least square methods for estimating parameters some models are discussed, which used models. finding useful practitioners their selection