v0.2.3

Pingouin v0.2.3

Diff since v0.2.1

• Updated dependencies,
• Prevented wrong tails for correlation.

Closed issues:

• Performance enhancement (#2)
• LoadError: Some tests did not pass when running julia test/runtests.jl (#5)

Merged pull requests:

• Update dependencies and add CI (#6) (@rikhuijzer)
• Relax compat entries (#7) (@rikhuijzer)
• Add CompatHelper (#8) (@rikhuijzer)
• Add TagBot (#9) (@rikhuijzer)

v0.2.2 - Correlations

Added support for correlations

v0.2.1 - Updated Non-Parametric tests and replaced SciPy

• Updated Non-parametric tests,
• Replaced SciPy by QuadGK for Bayesian tests,
• Optimizations.

v0.1.0 - Added Effect Sizes and CI

Compute effect sizes between two Arrays:

• 'cohen': Unbiased Cohen d
• 'hedges': Hedges g
• 'glass': Glass delta
• 'r': correlation coefficient
• 'eta-square': Eta-square
• 'odds-ratio': Odds ratio
• 'auc': Area Under the Curve
• 'cles': Common Language Effect Size

Convert pearson's r and cohen's d to:

• 'cohen': Unbiased Cohen d
• 'hedges': Hedges g
• 'eta-square': Eta-square
• 'odds-ratio': Odds ratio
• 'AUC': Area Under the Curve

Compute effect sizes from T-values.
Parametric confidence intervals around a Cohen d or a correlation coefficient.
Bootstrapped confidence intervals of univariate and bivariate functions.

v0.0.1 - Initial release

First alpha release. Pingouin.jl is a statistical library for users wanting simple yet exhaustive statistics.

Currently support:

• Anderson-Darling test of distribution,
• Geometric standard (Z) score,
• Levene & Bartlett tests,
• Shapiro-Wilk, Shapiro-Francia and Jarque Bera tests of normality,
• Mauchly and JNS tests for sphericity.