A Methodology to improve Goodness of Fit when Replicating Empirical Data utilizing Artificial Intelligence

Scientists and practitioners frequently resort to replicating empirical data when testing the validity of scientific theories or testing hypothesis. Commonly known probability distribution (Normal, Binomial, Exponential, etc.) are habitually assumed to fit the empirical data. To avoid complicated probability distributions, analysts find themselves tolerating poor values for the goodness of fit. In this paper, a methodology is introduced for replicating empirical data that succeeded in obtaining goodness of fit close to 100% compared to 87% goodness of fit using a known probability distribution. Moreover, Artificial Intelligence (AI) is developed spatially for this research to enhance accuracy further.