A/B Testing in Python
Learn the practical uses of A/B testing in Python to run and analyze experiments. Master p-values, sanity checks, and analysis to guide business decisions.
Start Course for Free4 hours16 videos51 exercises6,307 learnersStatement of Accomplishment
Create Your Free Account
or
By continuing, you accept our Terms of Use, our Privacy Policy and that your data is stored in the USA.Training 2 or more people?
Try DataCamp for BusinessLoved by learners at thousands of companies
Course Description
In this course, you will dive into the world of A/B testing, gain a deep understanding of the practical use cases, and learn to design, run, and analyze these A/B tests in Python.
Did you know that you are almost guaranteed to participate in an A/B test every time you browse the internet? From search engines and e-commerce sites to social networks and marketing campaigns — all businesses hire the best data analysts, scientists, and engineers to leverage the power of AB testing. Testing different variants can help optimize the customer experience, maximize profits, inform the next best design, and much more.
You’ll start by learning how to define the right metrics before learning how to estimate the appropriate sample size and duration to yield conclusive results. Throughout this course, you’ll use a range of Python packages to help with A/B testing, including statsmodels, scipy, and pingouin.
By the end of the course, you will be able to run the necessary checks that guarantee accurate results, master the art of p-values, and analyze the results of A/B tests with ease and confidence to guide the most critical business decisions.
Discover How A/B Tests Work
Did you know that you are almost guaranteed to participate in an A/B test every time you browse the internet? From search engines and e-commerce sites to social networks and marketing campaigns — all businesses hire the best data analysts, scientists, and engineers to leverage the power of AB testing. Testing different variants can help optimize the customer experience, maximize profits, inform the next best design, and much more.
Learn About A/B Testing in Python
You’ll start by learning how to define the right metrics before learning how to estimate the appropriate sample size and duration to yield conclusive results. Throughout this course, you’ll use a range of Python packages to help with A/B testing, including statsmodels, scipy, and pingouin.
By the end of the course, you will be able to run the necessary checks that guarantee accurate results, master the art of p-values, and analyze the results of A/B tests with ease and confidence to guide the most critical business decisions.
Training 2 or more people?
Get your team access to the full DataCamp platform, including all the features.In the following Tracks
Applied Statistics in Python
Go To Track- 1
Overview of A/B Testing
FreeIn this chapter, you’ll learn the foundations of A/B testing. You’ll explore clear steps and use cases, learn the reasons and value of designing and running A/B tests, and discover the most commonly used metrics design and estimation frameworks.
- 2
Experiment Design and Planning
In Chapter 2, you’ll cover the experiment design process. Starting with learning how to formulate strong A/B testing hypotheses, you’ll also cover statistical concepts such as power, error rates, and minimum detectable effects. You’ll finish the chapter by learning to estimate the appropriate sample size needed to yield conclusive results and tackle scenarios with multiple comparisons.
Hypothesis formulation and distributions50 xpStrong hypothesis formulation50 xpPlotting distributions100 xpCentral limit theorem for means100 xpExperimental design: setting up testing parameters50 xpInterpreting p-values100 xpError rates in the wild50 xpExperimental design: power analysis50 xpPlotting power curves100 xpSample size for means100 xpSample size for proportions100 xpMultiple comparisons tests50 xpIs a multiple comparisons correction needed?100 xpCorrected p-values100 xp - 3
Data Processing, Sanity Checks, and Results Analysis
Here, you’ll discover a concrete workflow for cleaning, preprocessing, and exploring AB testing data, as well as learn the necessary sanity checks we need to follow to ensure valid results. You’ll explore a detailed explanation and example of analyzing difference in proportions A/B tests.
Data cleaning and exploratory analysis50 xpProportions EDA100 xpA/B test data cleaning100 xpSanity checks: Internal validity50 xpSRM100 xpDistributions balance100 xpSanity checks: external validity50 xpNovelty effects detection100 xpSimpson's paradox in action100 xpAnalyzing difference in proportions A/B tests50 xpDifference in proportions A/B test100 xpInterpretation of confidence intervals50 xpConfidence intervals for proportions100 xp - 4
Practical Considerations and Making Decisions
In the final chapter, you’ll develop frameworks for analyzing differences in means and leveraging non-parametric tests when several assumptions aren't met. You’ll also learn how to apply the Delta method when analyzing ratio metrics and discover the best practices and some advanced topics to continue the A/B testing mastery journey.
Analyzing difference in means A/B tests50 xpT-test for difference in means100 xpPairwise t-tests100 xpNon-parametric statistical tests50 xpParametric or non-parametric?100 xpMann-Whitney U test100 xpChi-square test for independence100 xpRatio metrics and the delta method50 xpDelta or not?100 xpDelta method100 xpA/B Testing best practices and advanced topics intro50 xpBest practices50 xpDay-of-the-week effect100 xpWrap-up: A/B testing in python50 xp
Training 2 or more people?
Get your team access to the full DataCamp platform, including all the features.In the following Tracks
Applied Statistics in Python
Go To Trackcollaborators
prerequisites
Hypothesis Testing in Python
Moe Lotfy, PhDPrincipal Data Science Manager
Moe is a Principal Data Science Manager with 10+ years of experience working in the fields of data science and analytics in various settings including research, academia, and industry. He combines his physics/engineering domain knowledge with data science expertise to uncover insights in massive datasets, influence critical design decisions, and drive product improvements. Over his career, he has advised and built analytics and experimentation functions for several fortune 500 companies. He fuels his passion for Data Science/AI through teaching and giving invited lectures/talks. Moe has a PhD in Nuclear Fusion Engineering from UCLA with a focus on experimentation and computational analysis, and a BSc in Mechanical and Aerospace Engineering from the University of Illinois at Urbana-Champaign. His areas of expertise include energy systems, AI, autonomous driving, shipping high-impact products, and all things data and experimentation.
What do other learners have to say?
FAQs
Join over 15 million learners and start A/B Testing in Python today!
Create Your Free Account
or
By continuing, you accept our Terms of Use, our Privacy Policy and that your data is stored in the USA.