A Goodness-of-Fit Test Based on Fuzzy Random Variables

During the last decades, several methods have been proposed for Kolmogorov−Smirnov one-sample test based on fuzzy random variables to describe impression of classical variables. However, such techniques do not discuss modeling imprecise observations and simulation data from distribution a variable. Moreover, rely cumulative function with known parameters. In this paper, however, modified is introduced novel notion which comes down model fuzziness randomness in population frequently used family probability distributions called location scale functions. A method moment estimator was also utilized estimate Then, non-fuzzy developed hypotheses. Monte Carlo employed evaluate critical value corresponding significance level performance using power studies. Comparing observed statistics given level, procedure finally accept or reject null hypothesis. Two numerical examples including study an applied example were provided clarify discussions paper. The compared some existing methods. goodness-of-fit results demonstrated that provides efficient tool handle statistical inference observations.