Many lifetime distributions are motivated only by mathematical interest. Here, eight new families of distributions are introduced. These distributions are motivated as models for the stress of a system consisting of components working in parallel/series and each component has a fixed number of sub-components working in parallel/series. Mathematical properties and estimation procedures are derived for one of the families of distributions. A real data application shows superior performance of a three-parameter distribution (performance assessed with respect to Kolmogorov-Smirnov statistics, AIC values, BIC values, CAIC values, AICc values, HQC values, probability-probability plots, quantile-quantile plots and density plots) versus thirty one other distributions, each having at least three parameters.\\
The paper gives some basic ideas of both the construction and investigation of the properties of the Bayesian estimates of certain parametric functions of the parent exponential distribution under the model of random censorship assuming the Koziol-Green model. Various prior distributions are investigated and the corresponding estimates are derived. The stress is put on the asymptotic properties of the estimates with the particular stress on the Bayesian risk. Small sample properties are studied via simulations in the special case.