Path 4: Hypothesis Testing & Inference (The Proof)

Welcome to the final frontier of core statistics.

Let’s look at how far you have come. In Path 1, you learned how to define and collect data without ruining it. In Path 2, you learned how to describe the data sitting in front of you. In Path 3, you learned the rules of probability, the Bell Curve, and the Central Limit Theorem.

You now have all the puzzle pieces. It is time to put them together and actually use them to make decisions.

In the real world, data scientists are constantly asked to prove things: Did this new website design actually increase sales, or was it just a lucky week? Does this new drug actually lower blood pressure, or is it a placebo effect? Is the marketing campaign working?

You cannot answer these questions with a simple “yes” or “no.” You have to answer them with a mathematical probability. This is called Inferential Statistics, and the process we use to do it is called Hypothesis Testing.

In this module, you will learn the exact tests data scientists use to separate mathematical truth from random luck.

What You Will Learn in This Path

This module transitions you from abstract probability into practical, real-world testing. We have broken this down into five sequential lessons:

• Step 1: The Framework of Proof: Null Hypotheses & P-Values Learn the “innocent until proven guilty” framework of data science. You will learn how to set up a test, what an Alpha level is, and how to read a P-Value without falling into the most common traps.
• Step 2: Confidence Intervals: The Margin of Error You can almost never know the exact true average of an entire population. Learn how to use Z-scores to build a safety net, allowing you to say, “I am 95% confident the true number is between X and Y.”
• Step 3: T-Tests: Comparing Two Worlds The bread-and-butter of business analytics and A/B testing. Learn exactly how to compare the averages of two different groups to see if the difference between them is statistically significant.
• Step 4: ANOVA: Comparing Three or More Worlds Why can’t you just run a bunch of T-Tests if you have 4 different groups? Because it ruins the math. Learn how Analysis of Variance (ANOVA) allows you to test multiple groups at the exact same time without inflating your error rate.
• Step 5: Chi-Square Tests: Testing Categories T-Tests and ANOVA are for continuous numbers. But what if you want to test categories? We loop all the way back to Path 1 to learn how to test nominal data (e.g., “Is there a relationship between gender and voting preference?”).
• Step 6: Final Knowledge Check Quiz on Hypothesis Testing & Inference.

Ready to start testing?

➡️ Click here to begin Step 1: The Framework of Proof