Review of using of Bayes-Fiducial (BF) approach for solution of some important statistical problem is given. BF decision is always a function of sufficient statistics (even in case when sufficient statistics coincides with the sample itself (for example, for Weibull distribution)). By contrast with maximum likelihood method BF decision is based on the use of specific loss function. By contrast with Bayes decision it does not need a priori distribution of unknown parameters. For the distributions with location and/or scale parameter the solutions of the following problems are considered: point estimates of location and scale parameters, p-bound (prediction limit) calculation and specified life nomination with specific loss function. Numerical examples are given.