Scribe logoScribeNotes & practice
Sign inStart free
  1. Notes
  2. ›AP Statistics
  3. ›3 Inference for Categorical Data: Proportions
  4. ›3.6 p-values

AP Statistics · Unit 3 · Inference for Categorical Data: Proportions

3.6 p-values

Interpret a p-value in context, explain what small and large p-values suggest about the null hypothesis, and separate statistical from practical significance.

  • 4 min read
  • 5 parts
  • 10 questions
  • Draft
Start a Quick 5 on this topic→Jump to the 10 questions
1/5A p-value measures how unusual the sample result is
  1. 1A p-value measures how unusual the sample result is
  2. 2The p-value is an area in the tail of the null model
  3. 3Interpreting a p-value names the null, the result, and the context
  4. 4A small p-value is strong evidence against the null hypothesis
  5. 5A statistically significant result may still be too small to matter
  6. Check your recall
  7. Practice: 10 questions
1

Part 1 of 5: A p-value measures how unusual the sample result is

Suppose a game maker says a coin lands heads half the time. You flip it 100 times and get 62 heads. A fair coin could do that, but it would be unusual.

The null hypothesis is the claim being tested, a specific value for the population proportion. A p-value puts a number on how unusual the result is. It assumes the null hypothesis is true, then asks how likely a result at least this extreme would be.

Common mistake

The p-value is not the probability that the null hypothesis is true. It assumes the null is true and describes the data.

Key term

p-value

The p-value is the probability, assuming the null hypothesis is true, of getting a sample proportion at least as extreme as the one observed.

Part 1 done

2

Part 2 of 5: The p-value is an area in the tail of the null model

Now picture where that probability comes from. If the null hypothesis were true, sample proportions would pile up around the null value in a bell shape. Your observed result sits somewhere on that curve.

The p-value is the area in the tail beyond your result. A one-sided alternative uses one tail. A two-sided alternative counts both tails, so its p-value is double the one-tail area.

Figure 1. The shaded tail is the probability, under the null model, of a sample proportion at least as extreme as the result.

A result far out in the tail leaves little area, which gives a small p-value. The curve shows the null model only. It describes what random sampling would produce if the claim were true.

Part 2 done

Quick check

One question on the part you just read

Easy

A p-value is calculated under which assumption?
Show answer and explanation

Answer: A · Worked explanation

The p-value asks how likely a result at least this extreme would be if the null hypothesis were true. It does not assume the alternative, and it does not assume that the sample proportion equals the population proportion. Those would defeat the purpose of the comparison.
3

Part 3 of 5: Interpreting a p-value names the null, the result, and the context

Interpreting a p-value follows a fixed pattern. Each part has a job. A vague answer, such as the chance that the claim is true, is incorrect.

  • Assume the null hypothesis is true, using the claimed value in context.
  • Describe a sample result at least as extreme as the one observed.
  • Give the probability, and say it comes from random sampling.

Worked example

Interpreting a p-value in context

A shop claims that 40% of its customers use a loyalty card. In a random sample of 200 customers, 47% use one. A test of H0:p=0.40H_0: p = 0.40H0​:p=0.40 against Ha:p>0.40H_a: p > 0.40Ha​:p>0.40 gives a p-value of about 0.022. Interpret the p-value.
  1. 1
    Assume the null is true: exactly 40% of all customers use a loyalty card.
  2. 2
    The sample result was 47%, so at least as extreme means 47% or higher.
  3. 3
    Write the probability in context: 0.022 is about 2.2%.

Answer: If 40% of all the shop’s customers use a loyalty card, there is about a 2.2% chance that a random sample of 200 customers has 47% or more users.

The statement is conditional. It begins by assuming the claim is true, because that assumption is what the p-value is built on.

Part 3 done

4

Part 4 of 5: A small p-value is strong evidence against the null hypothesis

Now ask what the number means for the claim. A small p-value says the result would be unusual if the null hypothesis were true. That is evidence against the null. A large p-value says the result is not unusual, so the evidence against the null is weak.

To decide how small is small, compare the p-value with the significance level, α\alphaα. Common choices are 0.05 and 0.01. A result with a p-value at or below α\alphaα is statistically significant.

What different p-values suggest

p-valueResult under the nullEvidence against the null
Very small, such as 0.001Very unusualVery strong
Small, at or below α\alphaαUnusualConvincing
Large, above α\alphaαNot unusualNot convincing
p-value
Very small, such as 0.001
Result under the null
Very unusual
Evidence against the null
Very strong
p-value
Small, at or below α\alphaα
Result under the null
Unusual
Evidence against the null
Convincing
p-value
Large, above α\alphaα
Result under the null
Not unusual
Evidence against the null
Not convincing

Exam tip

Describe evidence with words such as convincing or not convincing. Do not say the null hypothesis is proven true or false.

Key terms · tap one for its definition

significance level

The significance level α\alphaα is a cutoff, set before seeing data, at or below which a p-value counts as convincing evidence against the null hypothesis.

statistically significant

Statistically significant describes a result whose p-value is at or below the chosen significance level α\alphaα.

Part 4 done

Quick check

One question on the part you just read

Easy

What does a small p-value suggest?
Show answer and explanation

Answer: B · Worked explanation

A small p-value means the data would be surprising under the null, which is convincing evidence against it. Evidence is not proof, so the null is not proven false. Sample size is not the issue here, because the p-value already accounts for it. Saying the null is probably true reverses the meaning of a small value.
5

Part 5 of 5: A statistically significant result may still be too small to matter

Significance has a second side in practice. We also ask about practical significance, which is whether an effect is large enough to matter in real life. The p-value alone cannot answer that.

Sample size drives the gap. A huge sample can give a small p-value for a tiny difference. A small sample can give a large p-value for a big one.

For example, 40,000 users with a success rate of 50.5% can be statistically significant against a claim of 50%. A half-point difference may not matter to anyone.

Common mistake

A small p-value does not show a large effect. It shows only that the result is unlikely to be random variation alone.

Key term

practical significance

Practical significance is whether the size of a difference or effect is large enough to matter in the real situation.

Note read

Check your recall[12 marks]

5 written questions. Answer each one in your head or on paper, then open the mark scheme.

  1. 1.Describe[3 marks]

    A test of H0:p=0.25H_0: p = 0.25H0​:p=0.25 against Ha:p>0.25H_a: p > 0.25Ha​:p>0.25 about the proportion of students who ride a bus gives a p-value of 0.03 for a sample proportion of 0.31. Describe what the p-value means in context.

    Show mark schemeHide mark scheme

    Model answer

    If 25% of all students ride a bus, there is about a 3% chance of a random sample giving a proportion of 0.31 or higher.

    • 1 mark for assuming the null is true, that 25% of all students ride a bus
    • 1 mark for referring to a sample proportion of 0.31 or greater
    • 1 mark for giving the probability as about 3%, from random sampling
  2. 2.Explain[2 marks]

    Explain what a small p-value suggests about the null hypothesis.

    Show mark schemeHide mark scheme

    Model answer

    A small p-value means the result would be unusual if the null hypothesis were true. This gives convincing evidence against the null hypothesis.

    • 1 mark for stating that the result would be unusual if the null were true
    • 1 mark for concluding that there is convincing evidence against the null hypothesis
  3. 3.Identify[2 marks]

    Identify whether a p-value of 0.08 is statistically significant at α=0.05\alpha = 0.05α=0.05, and give a reason.

    Show mark schemeHide mark scheme

    Model answer

    It is not statistically significant, because 0.08 is greater than 0.05.

    • 1 mark for identifying the result as not statistically significant
    • 1 mark for comparing 0.08 with the significance level of 0.05
  4. 4.Explain[3 marks]

    Explain why a statistically significant result might not be practically significant.

    Show mark schemeHide mark scheme

    Model answer

    A very large sample can give a small p-value even when the difference is tiny. The p-value does not measure the size of the effect. A tiny difference may be too small to matter in the real situation.

    • 1 mark for stating that a large sample can give a small p-value for a tiny difference
    • 1 mark for stating that the p-value does not measure effect size
    • 1 mark for linking a tiny difference to not mattering in practice
  5. 5.Describe[2 marks]

    Describe the mistake in saying that a p-value of 0.03 means there is a 3% chance the null hypothesis is true.

    Show mark schemeHide mark scheme

    Model answer

    The p-value assumes the null hypothesis is true. It is the probability of a result at least this extreme, not the probability that the null is true.

    • 1 mark for stating that the p-value is calculated assuming the null is true
    • 1 mark for stating that it is the probability of the result, not of the null hypothesis

Practice this topic

10 quick-fire multiple-choice questions, easy to hard. Tap an answer to see if you're right and the worked explanation. (The written questions with mark schemes are under “Check your recall” above.)

0 right0 of 10 answered

Includes the 2 quick checks in the note above.

3.

Easy·Identify[1 mark]

Identify which p-value gives the strongest evidence against the null hypothesis.
Show answer and explanation

Answer: C · Worked explanation

The smaller the p-value, the more unusual the result is under the null, so 0.003 gives the strongest evidence. The value 0.40 is the largest and gives the weakest evidence, because a result like that would be common if the null were true.
4.

Medium[1 mark]

A test gives a p-value of 0.037. Determine the conclusion at α=0.05\alpha = 0.05α=0.05 and at α=0.01\alpha = 0.01α=0.01.
Show answer and explanation

Answer: D · Worked explanation

A result is convincing when the p-value is at or below the significance level. Since 0.037 is below 0.05, it is convincing at that level, and since 0.037 is above 0.01, it is not convincing at that level. Reversing the two levels gives the wrong pattern.
5.

Medium[1 mark]

A test of H0:p=0.60H_0: p = 0.60H0​:p=0.60 against Ha:p>0.60H_a: p > 0.60Ha​:p>0.60 about the proportion of people who recycle gives a p-value of 0.014. Identify the best interpretation.
Show answer and explanation

Answer: A · Worked explanation

The p-value is a conditional probability that assumes the null value, 0.60, and refers to a result at least as extreme as the one seen. It is not the probability that the null is true, nor the probability of the alternative. It is not a percentage of the sample.
6.

Medium[1 mark]

In a random sample of 100,000, the sample proportion is 0.504 and the test of H0:p=0.50H_0: p = 0.50H0​:p=0.50 against Ha:p>0.50H_a: p > 0.50Ha​:p>0.50 gives a p-value of 0.006. Which comment is best?
Show answer and explanation

Answer: B · Worked explanation

A p-value of 0.006 is below common significance levels, so the result is statistically significant. The tiny difference of 0.004 may not matter in the real situation, so practical significance is doubtful. A small p-value alone does not make an effect important.
7.

Medium[1 mark]

A test gives a p-value of 0.35. Which statement is correct?
Show answer and explanation

Answer: C · Worked explanation

A large p-value means the result is not unusual under the null, so the evidence against it is weak. That does not show the null is true. The value 0.35 is a probability about the data, assuming the null, not a probability about the null itself.
8.

Hard[2 marks]

Two studies each test H0:p=0.50H_0: p = 0.50H0​:p=0.50 and each finds a sample proportion of 0.54. Study A uses n=100n = 100n=100, and Study B uses n=2,500n = 2{,}500n=2,500. Which statement is correct?
Show answer and explanation

Answer: A · Worked explanation

A larger sample has less sampling variation, so a difference of 0.04 is more surprising and the p-value is smaller. For Study A the standard deviation is 0.05, giving a difference of 0.8 standard deviations. For Study B it is 0.01, giving 4 standard deviations. The sample proportion alone does not fix the p-value.
9.

Hard[2 marks]

A researcher finds a p-value of 0.03 and says, “There is only a 3% chance the result was due to chance, so I am 97% sure the alternative is true.” Which critique is best?
Show answer and explanation

Answer: D · Worked explanation

The p-value is the probability of a result at least this extreme if the null is true. It does not give the probability that the null or the alternative is true. A p-value of 0.03 is significant at α=0.05\alpha = 0.05α=0.05, but that does not turn it into a 97% certainty.
10.

Hard[2 marks]

Two similar studies test the same claim at α=0.05\alpha = 0.05α=0.05. One gets a p-value of 0.049, and the other gets 0.051. Which statement is best?
Show answer and explanation

Answer: B · Worked explanation

The two p-values are almost identical, so the evidence is almost equally strong. The cutoff of 0.05 forces different labels, but the data do not differ much. Neither study proves a hypothesis, and a p-value above α\alphaα does not show that no effect exists.

Keep going

Next topic3.7 Carrying out a test for a proportionPrevious topic3.5 Setting up a test for a proportion

More in Unit 3 · Inference for Categorical Data: Proportions

  1. 3.2Sample proportionsNotes · 9 questions
  2. 3.3Confidence interval for a proportionNotes · 10 questions
  3. 3.4Claims from a proportion intervalNotes · 10 questions
  4. 3.5Setting up a test for a proportionNotes · 10 questions
  5. 3.6p-valuesNotes · 10 questions
  6. 3.7Carrying out a test for a proportionNotes · 10 questions
  7. 3.8Errors in testsNotes · 10 questions
  8. 3.9Differences in sample proportionsNotes · 10 questions
  9. 3.10Interval for a difference of proportionsNotes · 10 questions

All AP Statistics topics →

Draft: written by Scribe and checked automatically, not yet by a subject reviewer.

Practice questions are original, written by Scribe and checked automatically for correctness.

Topic codes follow the official numbering. Not endorsed by College Board or any exam board.

On this page

0/5 read

  1. 1A p-value measures how unusual the sample result is
  2. 2The p-value is an area in the tail of the null model
  3. 3Interpreting a p-value names the null, the result, and the context
  4. 4A small p-value is strong evidence against the null hypothesis
  5. 5A statistically significant result may still be too small to matter
  6. Check your recall
  7. Practice: 10 questions
All coursesScribeHow it worksPricingPrivacyTerms

Notes and questions are written by Scribe in our own words. Topic codes follow the official course numbering so you can find your place. Not produced or endorsed by the IB, College Board, AQA, OCR, Pearson Edexcel or any exam board.

© 2026 Scribe