Course contentsShow
← Data Science
Lesson 317 of 2,1459. Hypothesis Testing FoundationsFree lesson

Sampling Distribution of the Test Statistic

Understand how test statistics follow known distributions under the null hypothesis, enabling probability calculations.

Sampling Distribution of the Test Statistic

You'll learn: How test statistics behave predictably under the null hypothesis, letting us calculate the probability of seeing our result by chance.

The Core Idea

When you calculate a test statistic (like a Z or t-value) from your sample, you're asking: "If the null hypothesis were actually true, how unusual is this number?"

Here's the key insight: if the null hypothesis is true, your test statistic isn't just a random number—it follows a known probability distribution. This distribution tells you what values are common versus rare when nothing special is happening in your population.

Think of it like a carnival game. If the game is fair (null hypothesis true), you know the distribution of possible scores. When someone gets an extremely high score, you can calculate: "What's the probability of scoring this high in a fair game?" A tiny probability suggests the game might not be fair after all.

Why This Matters

You've already learned that test statistics like Z and t summarize how far your sample result is from what the null hypothesis claims. Now you understand where the magic happens: these statistics follow distributions we can look up (standard normal for Z, t-distribution for t, etc.).

This is what makes hypothesis testing work! You can calculate a test statistic from your data, then use its sampling distribution to find the p-value—the probability of getting a result at least as extreme as yours if H₀ were true.

Key Takeaway: Under the null hypothesis, test statistics follow known distributions (Z ~ N(0,1), t ~ t-distribution, etc.), which allows us to calculate probabilities and make decisions about whether our data contradicts H₀.