Removing skewness and kurtosis by transformation when testing for mean equality

Abstract A transformation of the Welch statistic to compare means is proposed to correct skewness and kurtosis of parent populations. The results show that this transformation seems to improve the performance of the test in heavy-tailed distributions more than other transformations focused only on skewness. The proposed test outperforms the Welch test in asymmetric heavy-tailed distributions with high heteroscedasticity and it behaves better than the Johnson’s transformation trimmed mean Welch test in normal, near-normal and light-tailed distributions. It may also be a better option when some of the distributions are heavy-tailed and some light-tailed.

[1]  Rand R. Wilcox,et al.  Trimming, Transforming Statistics, And Bootstrapping: Circumventing the Biasing Effects Of Heterescedasticity And Nonnormality , 2002 .

[2]  J. J. Dijkstra,et al.  Testing the equality of several means when the population variances are unequal , 1981 .

[3]  Rand R. Wilcox,et al.  Comparing the means of two independent groups , 2007 .

[4]  I. Parra-Frutos.  Controlling the Type I error rate by using the nonparametric bootstrap when comparing means. , 2014, The British journal of mathematical and statistical psychology.

[5]  Adjusting for Unequal Variances When Comparing Means in One-Way and Two-Way Fixed Effects ANOVA Models , 1989 .

[6]  T. C. Oshima,et al.  Type I Error Rates for Welch’s Test and James’s Second-Order Test Under Nonnormality and Inequality of Variance When There Are Two Groups , 1994 .

[7]  Jiin-Huarng Guo,et al.  A powerful transformation trimmed mean method for one-way fixed effects ANOVA model under non-normality and inequality of variances , 1999 .

[8]  T. Micceri.  The unicorn, the normal curve, and other improbable creatures. , 1989 .

[9]  Julia Kastner,et al.  Introduction to Robust Estimation and Hypothesis Testing , 2005 .

[10]  Peter Hall,et al.  On the Removal of Skewness by Transformation , 1992 .

[11]  Robert A. Cribbie,et al.  Tests for Treatment Group Equality When Data are Nonnormal and Heteroscedastic , 2007 .

[12]  David C. Hoaglin,et al.  Summarizing Shape Numerically: The g‐and‐h Distributions , 2011 .

[13]  H. Keselman,et al.  Consequences of Assumption Violations Revisited: A Quantitative Review of Alternatives to the One-Way Analysis of Variance F Test , 1996 .

[14]  R. Fisher,et al.  148: Moments and Cumulants in the Specification of Distributions. , 1938 .

[15]  Robert A. Cribbie,et al.  Effect of non-normality on test statistics for one-way independent groups designs. , 2012, The British journal of mathematical and statistical psychology.

[16]  B. L. Welch.  ON THE COMPARISON OF SEVERAL MEAN VALUES: AN ALTERNATIVE APPROACH , 1951 .

[17]  Roser Bono,et al.  Skewness and Kurtosis in Real Data Samples , 2013 .

[18]  H. Keselman,et al.  Consequences of Assumption Violations Revisited: A Quantitative Review of Alternatives to the One-Way Analysis of Variance F Test , 1996 .

[19]  An invertible transformation two-sample trimmed t-statistic under heterogeneity and nonnormality , 2000 .

[20]  Robustness , 2020, The Science of Quantitative Information Flow.

[21]  N. J. Johnson,et al.  Modified t Tests and Confidence Intervals for Asymmetrical Populations , 1978 .