Hypothesis Testing Fundamentals

College Depth 48 in the knowledge graph I know this Set as goal
Unlocks 1278 downstream topics
hypothesis-testing null-hypothesis alternative-hypothesis

Core Idea

Hypothesis testing is a method for deciding between two competing claims about a population parameter. The null hypothesis (H₀) represents the status quo or 'no effect'; the alternative hypothesis (H₁ or H_a) represents what we're testing for. A test statistic is computed from sample data, and a p-value gives the probability of observing such an extreme statistic if H₀ is true. We reject H₀ when the p-value is smaller than a predetermined significance level α (typically 0.05), but this does not prove H₀ is false—only that the data provide evidence against it.

How It's Best Learned

Set up hypotheses for realistic scenarios. Interpret p-values correctly: probability of data given H₀, not probability H₀ is true. Distinguish statistical significance from practical significance.

Common Misconceptions

Thinking p-value is the probability that H₀ is true. Confusing 'fail to reject' with 'accept.' Believing p < α proves the alternative is true. Forgetting that p-values measure evidence, not truth of hypotheses.

Explainer

Suppose a pharmaceutical company claims their drug reduces blood pressure. You cannot test every patient in the world, so you test a sample. Hypothesis testing gives you a principled framework for deciding whether your sample result is convincing enough to conclude the drug actually works — or whether it could just be random variation.

You start by setting up two competing claims. The null hypothesis (H₀) is the conservative, boring claim: "nothing is happening" — the drug has no effect, the coin is fair, the groups are identical. The alternative hypothesis (H₁) is what you are trying to demonstrate: "there is an effect." You never directly test H₁; instead, you ask how surprising your data would be *if H₀ were true*. This is where your knowledge of sampling distributions comes in: you know what the distribution of sample statistics looks like under H₀, so you can measure where your actual result falls.

The p-value is the probability of observing a test statistic at least as extreme as yours, assuming H₀ is true. A small p-value means your data are unlikely under H₀ — the evidence points against it. When the p-value falls below your pre-chosen threshold α (often 0.05), you reject H₀. Note carefully what this does and does not say: rejecting H₀ is not the same as proving H₁ is true, and a large p-value is not proof that H₀ is true — it just means you did not find enough evidence against it. The phrase is "fail to reject," not "accept."

The most persistent misconception in statistics is reading the p-value backwards: thinking p = 0.03 means "there is a 3% chance H₀ is true." That is wrong. The p-value is a probability about the *data given H₀*, not about H₀ given the data. To put probabilities on hypotheses you need Bayesian methods. What p = 0.03 actually says is: "if H₀ were true, only 3% of experiments like mine would produce results this extreme or more." That is evidence against H₀, but it is not a probability that H₀ is false.

Finally, statistical significance and practical significance are different things. With a very large sample, even a trivially small effect (a drug that lowers blood pressure by 0.001 mmHg) can yield p < 0.05. Always pair your p-value with an effect size or confidence interval to assess whether the result is meaningful in the real world, not just statistically detectable.

Practice Questions 3 questions

Prerequisite Chain

Counting to 10Counting to 20Understanding ZeroThe Number ZeroCounting to FiveOne-to-One CorrespondenceCombining Small Groups Within 5Addition Within 10Addition Within 20Two-Digit Addition Without RegroupingTwo-Digit Addition with RegroupingAddition Within 100Repeated Addition as MultiplicationMultiplication Facts Within 100Division as Equal SharingDivision as Grouping (Measurement Division)Division: Grouping (Repeated Subtraction) ModelDivision: Fair Sharing ModelDivision as Equal SharingDivision as GroupingBasic Division FactsDivision Facts Within 100Two-Digit by One-Digit DivisionDivision with RemaindersRemainders and Quotients in DivisionDivision Word ProblemsIntroduction to Long DivisionFactors and MultiplesPrime and Composite NumbersEquivalent FractionsRelating Fractions and DecimalsDecimal Place ValueReading and Writing DecimalsComparing and Ordering DecimalsAdding and Subtracting DecimalsMultiplying DecimalsDividing DecimalsDividing FractionsMixed Number ArithmeticOrder of OperationsInteger Order of OperationsVariable ExpressionsFunction Notation ReviewRandom Variables: Definition and ClassificationJoint and Marginal DistributionsConditional Distributions of Random VariablesRandom VariablesSampling DistributionsHypothesis Testing Fundamentals

Longest path: 49 steps · 202 total prerequisite topics

Prerequisites (2)

Leads To (16)