Dive into a comprehensive crash course on A/B testing for data science, covering essential concepts, statistical analysis, and practical implementation. Learn to formulate hypotheses, identify key metrics, design tests, and analyze results using Python. Explore in-depth topics including hypothesis testing, significance levels, pooled estimates, test statistics, and p-values. Apply your knowledge through a real-world case study, enhancing your understanding of A/B testing in business contexts. Master data visualization techniques using Matplotlib and Seaborn, perform power analysis, and evaluate both statistical and practical significance. By the end of this 2.5-hour tutorial, gain the skills to conduct and interpret A/B tests effectively, preparing you for data-driven decision-making in your data science career.
Overview
Syllabus
⌨️ Video Introduction
⌨️ Introduction to Data Science and A/B Testing
⌨️ Basics of A/B Testing in Data Science
⌨️ Key Parameters of A/B Testing for Data Scientists
⌨️ Formulating Hypotheses and Identifying Primary Metrics in Data Science A/B Testing
⌨️ Designing an A/B Test: Data Science Approach
⌨️ Resources for A/B Testing in Data Science
⌨️ Analyzing A/B Test Results in Python: Data Science Techniques
⌨️ Data Science Portfolio Project: Case Study with AB Testing
⌨️ Reintroduction to A/B Testing in the Data Science Process
⌨️ Data Science Techniques: Loading Data with Pandas for A/B Testing
⌨️ Data Science Visualization: Using Matplotlib and Seaborn for A/B Test Click Data
⌨️ Data Science Power Analysis: Understanding A/B Test Model Parameters
⌨️ Data Science Calculations: Pooled Estimates and Variance for A/B Testing
⌨️ Computing A/B Test P-Values: Data Science Methods for Statistical Significance
⌨️ Practical Significance in A/B Testing: A Data Science Perspective
⌨️ Conclusion: Wrapping Up A/B Testing in Data Science
Taught by
freeCodeCamp.org
