Solving linear regression without skewness of the residuals' distribution. Issue 8 (3rd August 2021)

• Record Type: Journal Article
• Authors: Ricker, Martin
• Is Part Of: Communications in statistics. Volume 50:Issue 8(2021)
• Page Start: 2482
• Page End: 2495
• Publication Date: 2021-08-03
• Subjects: Computer code -- generalized linear model -- multiple linear regression -- standardized residuals; Mathematical statistics -- Periodicals; Mathematical statistics -- Data processing -- Periodicals; Digital computer simulation -- Periodicals; 519.5
• DOI: 10.1080/03610918.2019.1614621
• Languages: English
• ISSNs: 0361-0918

Abstract

Abstract: Linear ordinary least squares (OLS) regression assumes an unskewed distribution of the residuals for correct inference and prediction. A proof is given that for Manly's exponential transformation of the dependent variable, there is always at least one solution for λ, such that the skewness of the standardized residuals' distribution is zero. A computer code in Mathematica, together with an illustrative example, are provided. Generalized linear models are discussed briefly in comparison.