pywayne-statistics
Pywayne Statistics provides a unified library for statistical hypothesis testing across normality assessment, group comparisons, correlation analysis, time series validation, and regression diagnostics. Each test returns consistent result objects with p-values, confidence intervals, and effect sizes, making it straightforward to validate data assumptions and detect significant effects in A/B tests and observational studies.
Pywayne Statistics performs hypothesis testing via 37+ methods including normality, location, correlation, time series, and model diagnostic tests.
AI-generated summary based on this skill's SKILL.md
Install
wangyendt/wayne-skills/statistics · repository language: Python
git clone https://github.com/wangyendt/wayne-skills
cp -r wayne-skills/pywayne/statistics ~/.claude/skills/statisticsFrequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What statistical hypothesis testing capabilities does pywayne-statistics provide?
Pywayne-statistics is a unified library for statistical hypothesis testing that covers normality assessment, group comparisons, correlation analysis, time series validation, and regression diagnostics. Each test returns consistent result objects with p-values, confidence intervals, and effect sizes, enabling straightforward validation of data assumptions and detection of significant effects in A/B tests and observational studies.
How can I perform a normality test with shapiro wilk in pywayne-statistics?
Pywayne-statistics includes normality testing functionality such as Shapiro-Wilk tests to assess whether your data follows a normal distribution. The test returns standardized result objects containing p-values and effect sizes, allowing you to determine if your data meets the normality assumption required by many parametric statistical methods.
Can pywayne-statistics help with A/B testing and statistical significance?
Yes, pywayne-statistics supports A/B testing and group comparison workflows. It provides two-sample t-tests, Mann-Whitney U tests for non-parametric comparisons, and ANOVA for multiple group comparisons. Each test delivers p-values, confidence intervals, and effect sizes to help you assess whether observed differences between groups are statistically significant.
What regression model diagnostics does pywayne-statistics offer?
Pywayne-statistics includes comprehensive regression diagnostics to validate model assumptions and identify issues. It provides heteroscedasticity testing, variance inflation factor (VIF) calculations for multicollinearity detection, residual analysis tools, and Durbin-Watson autocorrelation detection to ensure your regression models meet key statistical assumptions.
How does pywayne-statistics handle time series stationarity and autocorrelation?
Pywayne-statistics provides time series validation tools including ADF (Augmented Dickey-Fuller) stationarity tests and Ljung-Box autocorrelation testing. These functions help you assess whether your time series data is stationary and identify significant autocorrelation patterns, which are critical for proper time series modeling and forecasting.
What correlation and independence tests are available in pywayne-statistics?
Pywayne-statistics supports multiple correlation and independence testing approaches including Pearson and Spearman correlation tests for continuous variables, and chi-square independence tests for categorical data. All tests return consistent result objects with p-values and effect sizes, plus support for multiple testing p-value corrections when conducting many tests simultaneously.
SKILL.md
rendered from the published skill — quoted content, verbatim
Pywayne Statistics
Comprehensive statistical testing library for hypothesis testing, A/B testing, and data analysis.
Quick Start
from pywayne.statistics import NormalityTests, LocationTests
import numpy as np
# Test data normality
nt = NormalityTests()
data = np.random.normal(0, 1, 100)
result = nt.shapiro_wilk(data)
print(f"p-value: {result.p_value:.4f}, is_normal: {not result.reject_null}")
# Compare two groups
lt = LocationTests()
group_a = np.random.normal(100, 15, 50)
group_b = np.random.normal(105, 15, 50)
result = lt.two_sample_ttest(group_a, group_b)
print(f"Significant difference: {result.reject_null}")
Test Categories
NormalityTests (NormalityTests)
Test if data follows a
(truncated - see the full file via the links below)
Read as markdown · JSON record · Browse the source repository
File tree — 1 file
pywayne/statistics/SKILL.md