Kurtosis Statistics with Reference to Power Function Distribution

Abstract

Pearson statistics of skewness and kurtosis gave false impression to assess the peakedness and tailedness for skewed (moderately, J-shape or reverse J-shape) Distributions. A number of alternate measures were suggested in literature by Hosking (1992), Blest (2003), Elamir and Seheult (2003), and Fiori and Zenga (2005) that provided better interpretation than the Karl Pearson statistics. Power Function Distribution has the characteristics of symmetric, J-shape or reverse Jshape with varying magnitude of its shape parameter. In this paper, we derived the Blest‟s statistics of skewness and kurtosis, L-skewness and L-kurtosis and Trimmed L-skewness and Trimmed L-kurtosis for Power Function Distribution. Comparison is made with Karl Pearson statistics.