statistics-math

Files (6)

• SKILL.md
• config.yaml · assets/
• schema.json · assets/
• GUIDE.md · references/
• PATTERNS.md · references/
• validate.py · scripts/

SKILL.md (first lines)

# Statistics & Mathematics

Mathematical foundations for data science, machine learning, and statistical analysis.

## Quick Start

```python
import numpy as np
import scipy.stats as stats
from sklearn.linear_model import LinearRegression

# Descriptive Statistics
data = np.array([23, 45, 67, 32, 45, 67, 89, 12, 34, 56])
print(f"Mean: {np.mean(data):.2f}")
print(f"Median: {np.median(data):.2f}")
print(f"Std Dev: {np.std(data, ddof=1):.2f}")
print(f"IQR: {np.percentile(data, 75) - np.percentile(data, 25):.2f}")

# Hypothesis Testing
sample_a = [23, 45, 67, 32, 45]
sample_b = [56, 78, 45, 67, 89]
t_stat, p_value = stats.ttest_ind(sample_a, sample_b)
print(f"T-statistic: {t_stat:.4f}, p-value: {p_value:.4f}")

if p_value < 0.05:
    print("Reject null hypothesis: significant difference")
else:
    print("Fail to reject null hypothesis")
```

## Core Concepts

### 1. Probability Distributions

```python
import numpy as np
import scipy.stats as stats
import matplotlib.pyplot as plt

# Normal Distribution
mu, sigma = 100, 15
normal_dist = stats.norm(loc=mu, scale=sigma)
x = np.linspace(50, 150, 100)

# PDF, CDF calculations
print(f"P(X < 85): {normal_dist.cdf(85):.4f}")
print(f"P(X > 115): {1 - normal_dist.cdf(115):.4f}")
print(f"95th percentile: {normal_dist.ppf(0.95):.2f}")

# Binomial Distribution (discrete)
n, p = 100, 0.3
binom_dist = stats.binom(n=n, p=p)
print(f"P(X = 30): {binom_dist.pmf(30):.4f}")
print(f"P(X <= 30): {binom_dist.cdf(30):.4f}")

# Poisson Distribution (events per time)
lambda_param = 5
poisson_dist = stats.poisson(mu=lambda_param)
print(f"P(X = 3): {poisson_dist.pmf(3):.4f}")

# Central Limit Theorem demonstration
population = np.random.exponential(scale=10, size=100000)
sample_means = [np.mean(np.random.choice(population, 30)) for _ in range(1000)]
print(f"Sample means are approximately normal: mean={np.mean(sample_means):.2f}")
```

### 2. Hypothesis Testing Framework

```python
from scipy import stats
import numpy as np

class HypothesisTest:
    """Framework for statistical hypothesis testing."""

    @staticmethod
    def two_sample_ttest(group_a, group_b, alpha=0.05):
        """Independent samples t-test."""
        t_stat, p_value = stats.ttest_ind(group_a, group_b)
        effect_size = (np.mean(group_a) - np.mean(group_b)) / np.sqrt(
            (np.var(group_a) + np.var(group_b)) / 2
        )
        return {
            "t_statistic": t_stat,
            "p_value": p_value,
            "significant": p_value < alpha,
            "effect_size_cohens_d": effect_size
        }

    @staticmethod
    def chi_square_test(observed, expected=None, alpha=0.05):
        """Chi-square test for categorical data."""
        if expected is None:
            chi2, p_value, dof, expected = stats.chi2_contingency(observed)
        else:
            chi2, p_value = stats.chisquare(observed, expected)
            dof = len(observed) - 1
        return {
            "chi2_statistic": chi2,
            "p_value": p_value,
            "degrees_of_freedom": dof,
            "significant": p_value < alpha
        }

    @staticmethod
    def ab_test_proportion(conversions_a, total_a, conversions_b, total_b, alpha=0.05):
        """Two-proportion z-test for A/B testing."""
        p_a = conversions_a / total_a
        p_b = conversions_b / total_b
        p_pooled = (conversions_a + conversions_b) / (total_a + total_b)

        se = np.sqrt(p_pooled * (1 - p_pooled) * (1/total_a + 1/total_b))
        z_stat = (p_a - p_b) / se
        p_value = 2 * (1 - stats.norm.cdf(abs(z_stat)))

        return {
            "conversion_a": p_a,
            "conversion_b": p_b,
            "lift": (p_b - p_a) / p_a * 100,

From foryourhealth111-pixel/Vibe-Skills, Apache-2.0.

More from foryourhealth111-pixel/Vibe-Skills