Hypothesis Testing and p-Values

Use hypothesis testing and p-values to evaluate how compatible observed data are with a null hypothesis. Inspect Python outputs for Welch’s t-test on checkout times and a chi-square test of independence on email opens.

We'll cover the following...

Testing a difference in average checkout time
Testing an association between two categories
Reading a p-value before making a decision
Avoiding the common p-value errors

A checkout redesign reduces the observed average checkout time from 92 seconds to 84 seconds in two samples. That drop may reflect an improvement, or it may be sampling noise because samples differ even when the underlying process has not changed.

A null hypothesis ( $H_0$ ) states the baseline claim we test. For the checkout decision, $H_0$ says the new flow produces no difference in average checkout time. An alternative hypothesis ( $H_1$ ) states the competing claim. Here, $H_1$ says the average checkout time differs between flows. If the business question only permits a change that makes checkout faster, $H_1$ ...

1.Get Started

2.SQL for Data Analysis

3.From SQL to Python: Working with Data in NumPy and pandas

4.Statistics for Data Science

5.Data Cleaning and Exploratory Analysis

6.Feature Engineering

7.Data Visualization and Storytelling

8.Framing a Responsible ML Problem

9.Linear Regression and Model Evaluation

10.Classification Models

11.Generalization, Validation, and Regularization

12.Decision Trees

13.Classification Evaluation

14.Bagging and Random Forests

15.Gradient Boosting

16.Model Interpretability and Deployment

17.Unsupervised Learning: Clustering and Dimensionality Reduction

18.Time Series Fundamentals

19.Forecasting Models and Evaluation

20.Text Analytics

21.A/B Testing and Experimentation

22.Recommender Systems

23.Wrapping Up

Hypothesis Testing and p-Values