Verification of Accuracy in Statistical Estimations for Probability Distributions Having Tails of Special Shape

Statistical estimations for probability distributions having tails of special shape, such as a double-mode distri-bution well the so-called heavy-tailed or fat-tailed distribution, are quantitatively discussed through virtual experiments using computer simulations. In this paper, distribution describing damage degree concrete liners tunnels in cold region is examined an example distribution. First, data sets observations generated by use quasi-random numbers Pareto typical whereas actual set obtained used generating Next, statistical executed papers to identify showing “best” fitting among supposed plural candidates distributions. Finally, accuracy estimation quantified applying coefficient determination. The results show that tail scarcely improved even if number increased.