Random number generating method for generating random numbers in accordance with multivariate non-normal distributions based on the Yuan and Bentler method I on computer. The method includes application steps for applying n-dimensional multivariate non-normal distributions to n-dimensional experience distribution by using computer and steps for generating random numbers including pseudo-random numbers, quasi-random numbers, low discrepancy sequences, and physical random numbers by methods including additive generator method, M-sequence, generalized feedback shift-register method, and Mersenne Twister, and excluding congruential method, by using computer. The application steps use predetermined relationship equations for the third and fourth order moments to perform application associated with the third and fourth order moments of the empirical distributions. Moreover, by using random numbers generation method, parameters are estimated by maximum likelihood method. Furthermore, the random number generation method and the parameters estimated method are applied to simulation of financial field, semiconductor ion implantation, and the like.