Course contentsShow
← Data Science
Lesson 318 of 2,1459. Hypothesis Testing FoundationsFree lesson

What is a P-Value?

Define the p-value as the probability of observing data as extreme as yours if the null hypothesis were true.

What is a P-Value?

You'll learn: How to understand the p-value as the probability that measures how surprising your data is under the null hypothesis.

The Core Idea

A p-value is the probability of observing data as extreme as (or more extreme than) what you actually got, assuming the null hypothesis is true.

Think of it this way: imagine you're flipping a coin you suspect might be unfair. Your null hypothesis is "the coin is fair" (50/50 chance). You flip it 10 times and get 9 heads. The p-value answers: "If this coin really were fair, what's the chance I'd see 9 or more heads in 10 flips just by random luck?" If that probability is very small (say, 1%), you'd think, "Wow, that's really unlikely if the coin is fair—maybe it isn't fair after all."

Breaking It Down

The p-value tells you:

  • Small p-value (e.g., 0.01): Your observed data would be very rare if H₀ were true. This casts doubt on the null hypothesis.
  • Large p-value (e.g., 0.40): Your data isn't unusual at all under H₀. No strong reason to doubt the null.

The p-value does NOT tell you the probability that the null hypothesis is true—it's the probability of your data (or more extreme) given that H₀ is true.

Legal Analogy Revisited

From the "innocent until proven guilty" framework: the p-value is like asking, "If the defendant really is innocent, how likely is it we'd see evidence this incriminating?" Very unlikely evidence makes you question innocence.

Key Takeaway: The p-value measures how surprising your data is if the null hypothesis were true—smaller p-values suggest stronger evidence against H₀.