Open Source Web-Based Software to Evaluate Normal Distribution: Normality Assessment Software

Abstract

In this study, it was aimed to develop a new user-friendly web-based software that would easily test single-variable univariate and multivariate normal distribution suitability and enable users to get more accurate results in their studies.Shiny, an open source R package, was used to develop the proposed web software. In the developed software, Shapiro-Wilk and Anderson-Darling tests were used for the uniformity of univariate distribution, and Mardia's skewness-kurtosis, Henze-Zircon and Doornik-Hansen tests were used for multivariate normal distribution. Outputs for conformity to normal distribution were supported by using graphical methods. In practice, for the data set where each variable consisting of two variables derived by simulation has a standard normal distribution and the variables contain 1000 observations, the normal distribution conformity analysis has been performed. In the derived data set, each variable is normally distributed according to the Anderson-Darling and Shapiro-Wilk tests.In addition, the derived data set showed normal distribution with three variables according to Mardia's skewness-kurtosis and Henze-Zirkler tests. However, according to the Doornik-Hansen test, the triple does not show normal distribution.The developed software is a new user-friendly web-based software that can easily perform univariate and multivariate normal distribution conformity analysis and enable users to get more accurate results in their work. In further studies, Type I and Type II error types are planned to be included in the software in order to determine the best method.