Implements a moment-targeting normality transformation based on the simultaneous optimization of Tukey g-h distribution parameters. The method is designed to minimize both asymmetry (skewness) and excess peakedness (kurtosis) in non-normal data by mapping it to a standard normal distribution Cebeci et al (2026) <doi:10.3390/sym18030458>. Optimization is performed by minimizing an objective function derived from the Anderson-Darling goodness-of-fit statistic with Stephens's correction factor, utilizing the L-BFGS-B algorithm for robust parameter estimation. This approach provides an effective alternative to power transformations like Box-Cox and Yeo-Johnson, particularly for data requiring precise tail-behavior adjustment.
| Version: | 1.1.2 |
| Depends: | R (≥ 4.1.0) |
| Imports: | Rcpp, stats, doParallel, foreach, parallel, groupcompare |
| LinkingTo: | Rcpp |
| Suggests: | knitr, rmarkdown, readxl, writexl |
| Published: | 2026-03-17 |
| DOI: | 10.32614/CRAN.package.osktnorm (may not be active yet) |
| Author: | Zeynel Cebeci [aut, cre], Figen Ceritoglu [aut], Melis Celik Guney [aut], Adnan Unalan [aut] |
| Maintainer: | Zeynel Cebeci <cebeciz at gmail.com> |
| License: | GPL-2 | GPL-3 [expanded from: GPL (≥ 2)] |
| NeedsCompilation: | yes |
| Citation: | osktnorm citation info |
| Materials: | README |
| CRAN checks: | osktnorm results |
| Reference manual: | osktnorm.html , osktnorm.pdf |
| Vignettes: |
OSKT: Normality Transformation via Optimized Skewness and Kurtosis (source, R code) A Practical Example for Working with Datasets (source, R code) |
| Package source: | osktnorm_1.1.2.tar.gz |
| Windows binaries: | r-devel: not available, r-release: not available, r-oldrel: not available |
| macOS binaries: | r-release (arm64): not available, r-oldrel (arm64): not available, r-release (x86_64): not available, r-oldrel (x86_64): not available |
Please use the canonical form https://CRAN.R-project.org/package=osktnorm to link to this page.