---
title: "AP Statistics 3.5 Setting Up a Test for a Population Proportion"
description: "Review AP Stats 6.4 population proportion test setup, including H0 and Ha, one-sample z-test selection, random and 10% conditions, and large counts using p0."
canonical: "https://fiveable.me/ap-stats/unit-3/setting-up-test-for-population-proportion/study-guide/QLu7hUN0rwtnxLF7YdBT"
type: "study-guide"
subject: "AP Statistics"
unit: "Unit 3 – Inference for Categorical Data: Proportions"
lastUpdated: "2026-06-30"
---

# AP Statistics 3.5 Setting Up a Test for a Population Proportion

## Summary

Review AP Stats 6.4 population proportion test setup, including H0 and Ha, one-sample z-test selection, random and 10% conditions, and large counts using p0.

## Guide

Setting up a one-sample $z$ test for a [population proportion](/ap-stats/unit-5/sampling-distributions-for-sample-proportions/study-guide/Ezxev8MPpv3mFKjV4Gq3 "fv-autolink") means writing the [null and alternative hypotheses](/ap-stats/key-terms/null-and-alternative-hypotheses "fv-autolink"), naming the right test, and checking the conditions before you calculate anything. The null is always $H_0: p = p_0$, and your alternative uses $<$, $>$, or $\ne$ depending on what the question is looking for.

## Why This Matters for the AP Statistics Exam

[Unit 6](/ap-stats/unit-6 "fv-autolink") covers about 12 to 15 percent of the exam, and proportion tests show up in both multiple-choice and free-response work. Topic 6.4 is the setup stage, so getting it right sets you up for the later steps of finding the [p-value](/ap-stats/key-terms/p-value "fv-autolink") and stating a conclusion.

On the exam you will need to:

- Recognize when a one-sample [z-test](/ap-stats/key-terms/z-test "fv-autolink") for a proportion is the correct procedure for a single [categorical variable](/ap-stats/key-terms/categorical-variable "fv-autolink").
- Write clear hypotheses using correct notation.
- Verify conditions and show that work, which is important for clear, full-credit free-response answers.

This topic does not ask you to finish the test. It asks you to get the foundation right so the rest of the test holds up.

## Key Takeaways

- The [null hypothesis](/ap-stats/key-terms/null-hypothesis "fv-autolink") for a proportion is always H₀: p = p₀, where p₀ is the claimed value.
- The [alternative hypothesis](/ap-stats/key-terms/alternative-hypothesis "fv-autolink") uses <, >, or ≠ based on the question. One-sided uses < or >; two-sided uses ≠.
- A one-sided null may include ≥ or ≤, but it is still tested at the boundary of equality (p = p₀).
- The correct procedure for one categorical variable is a one-sample z-test for a population proportion.
- Check two condition groups: [independence](/ap-stats/key-terms/independence "fv-autolink") (random data plus the [10% condition](/ap-stats/key-terms/10percent-condition "fv-autolink")) and approximate normality (the large counts check).
- For the normality check in a test, use p₀, not p̂: confirm np₀ ≥ 10 and n(1 − p₀) ≥ 10.

## Writing Your Hypotheses

Every one-sample z-test for a proportion starts with two hypotheses: the null and the alternative.

### Null Hypothesis (H₀)

The null hypothesis is the statement assumed to be true unless the data give strong evidence against it. It usually represents no difference or no effect. For a proportion, it is always written as:

H₀: p = p₀

Here p₀ is the specific value claimed in the problem. For example, if a [claim](/ap-stats/unit-6/justifying-claim-based-on-confidence-interval-for-population-proportion/study-guide/YeTpyj6nyq03j0AJO3Bm "fv-autolink") says the population proportion is 0.5, then H₀: p = 0.5. You assume that value is correct until the [sample data](/ap-stats/key-terms/sample-data "fv-autolink") suggest otherwise.

### Alternative Hypothesis (Ha)

The alternative hypothesis is the statement you are collecting evidence for. It always uses a strict inequality:

- Ha: p < p₀ (one-sided, lower)
- Ha: p > p₀ (one-sided, upper)
- Ha: p ≠ p₀ (two-sided)

Use < or > when the question asks whether the true proportion is below or above the claimed value. Use ≠ when the question only asks whether the true proportion is different from the claimed value.

A quick note on [direction](/ap-stats/key-terms/direction "fv-autolink"): the null hypothesis for a one-sided test may be written with ≥ or ≤, but it is still tested at the boundary of equality, meaning p = p₀.

### Example

An article states that 94% of all people can identify the pop culture icon Baby Yoda. To test this claim, you poll a [random sample](/ap-stats/key-terms/random-sample "fv-autolink") of 750 people and find that 700 of them can correctly identify Baby Yoda. Do the data give evidence that the actual proportion is less than 94%?

This is a [population](/ap-stats/key-terms/population "fv-autolink") claim tested with a [sample](/ap-stats/unit-3/intro-planning-study/study-guide/YR5NI5ejwMAQ2dglm67s "fv-autolink"), so the right procedure is a one-sample z-test for a population proportion. Write the hypotheses:

- H₀: p = 0.94
- Ha: p < 0.94

## Checking Conditions

Before you run any calculations, you have to verify the conditions. Skipping this step or stating it vaguely costs you on free-response questions.

### Independence

Your data must come from a random sample or a randomized experiment. Without randomness, your sample could be [biased](/ap-stats/unit-5/biased-unbiased-point-estimates/study-guide/eZ5sR9XOkLB1o9KKpMHF "fv-autolink"), and no calculation fixes bias.

When sampling without replacement, also check the 10% condition: the sample size should be no more than 10% of the population (n ≤ 0.10N). This keeps the selections close enough to independent. State it like this: "It is reasonable to believe the population is at least 10 times the sample size, so independence is satisfied."

### Approximate Normality

You are using the normal curve to model the [sampling distribution](/ap-stats/unit-5/central-limit-theorem/study-guide/DPmpebCrsJBYfpSgOKn3 "fv-autolink") of p̂, so you need it to be approximately normal. For a test, check the large counts condition using p₀ (the null value), not the sample proportion:

- np₀ ≥ 10
- n(1 − p₀) ≥ 10

Both expected successes and expected failures must be at least 10.

### Example

For the Baby Yoda problem:

- Independence: "We poll a random sample of 750 people," and it is reasonable that the population is at least 7,500 people, so the 10% condition holds.
- Approximate normality: 750(0.94) = 705 expected successes and 750(0.06) = 45 expected failures. Both are at least 10, so the condition is met.

## Looking Ahead: Test Statistic and p-Value

Topic 6.4 stops at setup, but it helps to see where this leads. Once your hypotheses and conditions are set, the next step ([Topic 6.5](/ap-stats/unit-6/interpreting-p-values/study-guide/b0FEXf5MDjyQtz4Skz70 "fv-autolink")) is calculating the test statistic and p-value.

The standardized test statistic for a proportion is:

z = (p̂ − p₀) / √(p₀(1 − p₀)/n)

Notice that the standard error in a test uses p₀, the null value, not p̂. That matches the normality check, where you also used p₀. After you find z, you use the standard normal distribution to find the p-value, then compare it to your significance level to make a decision.

Your graphing calculator can speed this up. In the Stats Tests menu, choose 1-Prop Z-Test, enter your values, and it returns the z-score and p-value. Even when you use technology, still write your hypotheses and conditions clearly so your reasoning is visible.

## How to Use This on the AP Statistics Exam

### Free Response

- Define your parameter in context. State what p represents, such as "p = the true proportion of all people who can identify Baby Yoda."
- Write both hypotheses with correct notation and the right p₀ value.
- Match the inequality in Ha to the question. "More than" means >, "less than" means <, and "different from" means ≠.
- Show both condition checks with actual numbers, not just labels. Write out np₀ and n(1 − p₀) and compare them to 10.

### MCQ

- Be ready to pick the correct hypotheses from a list. Watch for the direction of the inequality.
- Know that the normality check for a test uses p₀, not p̂.
- Recognize a one-sample z-test for a proportion as the right method for a single categorical variable.

### Common Trap

- Putting an inequality in the null. The null for a proportion is always written as an equality at the boundary, H₀: p = p₀.

## Common Misconceptions

- Using p̂ in the normality check for a test. In a test you assume H₀ is true, so use p₀: np₀ ≥ 10 and n(1 − p₀) ≥ 10. The sample proportion p̂ is used for confidence intervals, not for the test condition.
- Choosing the alternative direction from the sample data. The direction of Ha comes from the [research question](/ap-stats/unit-8/carrying-out-chi-square-test-for-homogeneity-or-independence/study-guide/AmRuD3egBrZMCLGaBpMw "fv-autolink"), not from whether p̂ happened to land above or below p₀.
- Thinking the 10% condition is about the sample being large. It is about keeping selections approximately independent when sampling without replacement, so n must be small relative to the population.
- Believing a one-sided test means the null has an inequality you actually test. Even when the null is written with ≥ or ≤, it is tested at the boundary of equality, p = p₀.
- Skipping the parameter definition or context. Hypotheses without a clear definition of p in context are incomplete on free-response questions.

## Related AP Statistics Guides

- [Unit 6 Overview: Inference for Categorical Data: Proportions](/ap-stats/unit-6/review/study-guide/qB9o30Z14QZ1af2dduWq)
- [6.2 Constructing a Confidence Interval for a Population Proportion](/ap-stats/unit-6/constructing-confidence-interval-for-population-proportion/study-guide/rYCExLGlPYtMNFiJOWAR)
- [6.1 Introducing Statistics: Why Be Normal?](/ap-stats/unit-6/why-be-normal/study-guide/64N0FW5kF7jUylJbrOHf)
- [6.3 Justifying a Claim Based on a Confidence Interval for a Population Proportion](/ap-stats/unit-6/justifying-claim-based-on-confidence-interval-for-population-proportion/study-guide/YeTpyj6nyq03j0AJO3Bm)
- [6.5 Interpreting p-Values](/ap-stats/unit-6/interpreting-p-values/study-guide/b0FEXf5MDjyQtz4Skz70)
- [6.8 Confidence Intervals for the Difference of Two Proportions](/ap-stats/unit-6/confidence-intervals-for-difference-two-proportions/study-guide/YjPeyk5dGYBwzENoOU6S)

## Vocabulary

- **10% condition**: The requirement that sample size n is at most 10% of the population size N to ensure independence when sampling without replacement.
- **alternative hypothesis**: The claim that contradicts the null hypothesis, representing what the researcher is trying to find evidence for.
- **approximately normal**: A distribution that closely follows the shape of a normal distribution, allowing for the use of normal probability methods.
- **categorical variable**: A variable that takes on values that are category names or group labels rather than numerical values.
- **independence**: The condition that observations in a sample are not influenced by each other, typically ensured through random sampling or randomized experiments.
- **null hypothesis**: The initial claim or assumption being tested in a hypothesis test, typically stating that there is no effect or no difference.
- **number of failures**: The count of unfavorable outcomes in a sample, denoted as n(1-p̂), used to verify the normality condition.
- **number of successes**: The count of favorable outcomes in a sample, denoted as np̂, used to verify the normality condition.
- **one-sample z-test for a population proportion**: A hypothesis test used to determine whether a sample proportion provides evidence that a population proportion differs from a hypothesized value.
- **one-sided alternative hypothesis**: An alternative hypothesis that specifies the direction of the difference, either p₁ < p₂ or p₁ > p₂.
- **population proportion**: The true proportion or percentage of a characteristic in an entire population, typically denoted as p.
- **random sample**: A sample selected from a population in such a way that every member has an equal chance of being chosen, reducing bias and allowing for valid statistical inference.
- **randomized experiment**: A study design where subjects are randomly assigned to treatment groups to establish cause-and-effect relationships.
- **sample proportion**: The proportion of individuals in a sample that have a particular characteristic, denoted as p-hat (p̂).
- **sampling distribution**: The probability distribution of a sample statistic (such as a sample proportion) obtained from repeated sampling of a population.
- **sampling without replacement**: A sampling method in which an item selected from a population cannot be selected again in subsequent draws.
- **statistical inference**: The process of drawing conclusions about a population based on data collected from a sample.
- **two-sided alternative hypothesis**: An alternative hypothesis that specifies the difference could be in either direction, stated as p₁ ≠ p₂.

## FAQs

### How do you set up a test for a population proportion?

Define the parameter p in context, write H0: p = p0, choose the correct alternative hypothesis, identify the procedure as a one-sample z-test for a population proportion, and check the required conditions.

### What is H0 for a population proportion test?

The null hypothesis is H0: p = p0, where p0 is the claimed population proportion. The null is tested at the boundary of equality.

### How do you choose Ha for a population proportion test?

Use Ha: p < p0 for a lower one-sided test, Ha: p > p0 for an upper one-sided test, and Ha: p != p0 when the question asks whether the proportion is different.

### When do you use a one-sample z-test for a population proportion?

Use a one-sample z-test for a population proportion when you have one categorical variable and want to test a claim about a single population proportion.

### What conditions do you check for a population proportion test?

Check independence using random data and, when sampling without replacement, the 10% condition. Then check large counts using the null value: np0 >= 10 and n(1 - p0) >= 10.

### How is AP Stats 6.4 tested?

AP Stats 6.4 is tested through hypothesis notation, procedure selection, and condition checks. Free-response answers should define p in context and show the random, 10%, and large counts checks with numbers.

## Structured Data

```json
{"@context":"https://schema.org","@type":"FAQPage","inLanguage":"en","mainEntity":[{"@type":"Question","@id":"https://fiveable.me/ap-stats/unit-3/setting-up-test-for-population-proportion/study-guide/QLu7hUN0rwtnxLF7YdBT#how-do-you-set-up-a-test-for-a-population-proportion","name":"How do you set up a test for a population proportion?","acceptedAnswer":{"@type":"Answer","text":"Define the parameter p in context, write H0: p = p0, choose the correct alternative hypothesis, identify the procedure as a one-sample z-test for a population proportion, and check the required conditions."}},{"@type":"Question","@id":"https://fiveable.me/ap-stats/unit-3/setting-up-test-for-population-proportion/study-guide/QLu7hUN0rwtnxLF7YdBT#what-is-h0-for-a-population-proportion-test","name":"What is H0 for a population proportion test?","acceptedAnswer":{"@type":"Answer","text":"The null hypothesis is H0: p = p0, where p0 is the claimed population proportion. The null is tested at the boundary of equality."}},{"@type":"Question","@id":"https://fiveable.me/ap-stats/unit-3/setting-up-test-for-population-proportion/study-guide/QLu7hUN0rwtnxLF7YdBT#how-do-you-choose-ha-for-a-population-proportion-test","name":"How do you choose Ha for a population proportion test?","acceptedAnswer":{"@type":"Answer","text":"Use Ha: p < p0 for a lower one-sided test, Ha: p > p0 for an upper one-sided test, and Ha: p != p0 when the question asks whether the proportion is different."}},{"@type":"Question","@id":"https://fiveable.me/ap-stats/unit-3/setting-up-test-for-population-proportion/study-guide/QLu7hUN0rwtnxLF7YdBT#when-do-you-use-a-one-sample-z-test-for-a-population-proportion","name":"When do you use a one-sample z-test for a population proportion?","acceptedAnswer":{"@type":"Answer","text":"Use a one-sample z-test for a population proportion when you have one categorical variable and want to test a claim about a single population proportion."}},{"@type":"Question","@id":"https://fiveable.me/ap-stats/unit-3/setting-up-test-for-population-proportion/study-guide/QLu7hUN0rwtnxLF7YdBT#what-conditions-do-you-check-for-a-population-proportion-test","name":"What conditions do you check for a population proportion test?","acceptedAnswer":{"@type":"Answer","text":"Check independence using random data and, when sampling without replacement, the 10% condition. Then check large counts using the null value: np0 >= 10 and n(1 - p0) >= 10."}},{"@type":"Question","@id":"https://fiveable.me/ap-stats/unit-3/setting-up-test-for-population-proportion/study-guide/QLu7hUN0rwtnxLF7YdBT#how-is-ap-stats-64-tested","name":"How is AP Stats 6.4 tested?","acceptedAnswer":{"@type":"Answer","text":"AP Stats 6.4 is tested through hypothesis notation, procedure selection, and condition checks. Free-response answers should define p in context and show the random, 10%, and large counts checks with numbers."}}]}
```