Statistics for Data Science

Welcome to the "Statistical for Data Science" repository – your go-to resource for mastering essential statistical concepts in data science. This repository provides concise code implementations, analyses, and practical exercises, offering a seamless blend of theory and application. Whether you're a beginner seeking a solid foundation or an experienced practitioner aiming to enhance your statistical skills, this repository covers crucial topics like descriptive statistics, hypothesis testing, regression analysis, and more. Elevate your data science journey with clear explanations and hands-on coding. Happy exploring!

Data:

• US Health Insurance
• Marketing A/B testing
• Daily climate time series
• Drugs A, B, C, X, Y for Decision Trees

Descriptive Statistics

Statistical Experiments

Statistical experiments involve systematically collecting and analyzing data to test hypotheses or answer research questions.

1. A/B Testing: Compares two versions of a variable to determine which performs better.
2. Resampling: Technique that involves repeatedly drawing samples to obtain additional information about a population.
3. Power and Sample Size: Ensures experiments have sufficient sensitivity to detect meaningful effects.
4. Multi-Arm Bandit Algorithm: Optimization method for decision-making in scenarios with multiple treatment options.

Statistical Inference

Statistical inference involves making generalizations about populations based on sample data.

1. Hypothesis Tests: Evaluates evidence against a null hypothesis to make inferences about populations.
2. Statistical Significance and p-values: Determines the probability of observed results by chance.
3. t-Tests: Compares means between two groups.
4. Multiple Testing: Adjusts for increased risk of false positives when conducting multiple hypothesis tests.
5. ANOVA (Analysis of Variance): Compares means among three or more groups.
6. Chi-Square Test: Assesses independence between categorical variables.

Statistical Learning

• Resampling methods
• Machine learning and Deep Leraning for times series.

Stadistical modeling

• Statistical Models for Time Series: Autoregressive Models, Moving Average Models, Autoregressive Integrated Average Models

Programming

• R
• Python
• Julia