A SIMPLE TRANSFORMATION METHOD IN SKEWNESS REDUCTION

Statistical analysis of non-normal data is usually more complicated than that for normal distribution. In this paper, a simple root/power transformation technique developed by Niaki, et al [1] is extended to transform right and left skewed distributions to nearly normal. The value of the root/power is explored such that the skewness of the transformed data becomes almost zero with an acceptable error. The proposed method is then compared to the well-known and complicated Box, et al [2] transformation method for different left and right skewed distributions using Monte Carlo simulation. While the proposed procedure is easy to understand and to implement, the results of the simulation study show that it works as good as the Box-Cox method.