AP Statistics · Unit 3 · Inference for Categorical Data: Proportions
3.2 Sample proportions
Describe the sampling distribution of a sample proportion and check when a normal model fits it.
1/5A sample proportion turns a count into a fraction
- A sample proportion turns a count into a fraction
- The sample proportion is centered at the population proportion
- Larger samples give less variable sample proportions
- The shape is approximately normal when counts are large
- Three checks justify a normal model for the sample proportion
- Check your recall
- Practice: 9 questions
Part 1 of 5: A sample proportion turns a count into a fraction
A bakery tests a new recipe on 200 random customers. Each customer answers yes or no. Of them, 124 say they like it.
The fraction who like it is the sample proportion, written . Here . The fraction of all customers who like the recipe is the population proportion, written .
The value of is fixed but unknown. The value of changes with each random sample. So has its own distribution across samples, which the next section describes. This mirrors the sample mean, but for data with two outcomes.
Key terms · tap one for its definition
sample proportion
The sample proportion is the number of successes in a sample divided by the sample size .
population proportion
The population proportion is the fraction of all individuals in the population that have the characteristic of interest.
Part 2 of 5: The sample proportion is centered at the population proportion
Now imagine many random samples of 200 customers, each giving its own . Plot all of those values. The result is the sampling distribution of .
Its mean equals the population proportion: . Some samples give a above , and others give one below. On average they balance, so estimates do not run high or low.
Like any sampling distribution, it has a center, a spread, and a shape. The next two sections give the spread and the shape.
Key term
sampling distribution
The sampling distribution of a statistic is the distribution of its values over all possible samples of the same size from the population.

Quick check
One question on the part you just read
Easy
Show answer and explanation
Answer: C · Worked explanation
Part 3 of 5: Larger samples give less variable sample proportions
The spread of depends on the population proportion and the sample size. Its standard deviation is . This formula applies when the sample is no more than 10% of the population.
Because is in the denominator, larger samples give a smaller spread. Quadrupling halves . The product is largest at , so proportions near one half vary the most.
A bigger sample averages out chance variation. The proportions from different samples then stay closer to . Notice that the center does not move with , and only the spread changes.
Worked example
Mean and standard deviation of a sample proportion
- The mean is .
- The standard deviation is .
- Substitute: .
- Evaluate: .
Answer: The mean of is 0.40 and its standard deviation is about 0.049.
Part 4 of 5: The shape is approximately normal when counts are large
Center and spread are settled, so shape comes next. A sample proportion comes from counting successes, and the count can be skewed. Take and . Most samples hold 0 to 4 successes, and large counts are rare.
As the expected counts grow, the skew fades and the distribution becomes approximately normal. The large counts condition checks this. Here is the expected number of successes, and is the expected number of failures. Counting both is a quick test of shape.
Key term
large counts condition
The large counts condition requires that both and are at least 10, so the sampling distribution of is approximately normal.

Quick check
One question on the part you just read
Easy
Show answer and explanation
Answer: B · Worked explanation
Part 5 of 5: Three checks justify a normal model for the sample proportion
Before using a normal model, confirm three conditions. Write each one with the numbers from the problem.
- Random: the data come from a random sample.
- The 10% condition: the sample size is at most 10% of the population size .
- Large counts: both and are at least 10.
Sampling without replacement makes selections slightly dependent. Keeping at most 10% of makes this effect negligible. If any condition fails, do not use the normal model.
Worked example
Checking conditions
- Random: the sample is stated to be random.
- 10% condition: 10% of 5,000 is 500, and .
- Large counts: and .
- Standard deviation: .
Answer: All conditions are met. is approximately normal with mean 0.40 and standard deviation 0.040.
Key term
10% condition
The 10% condition requires that the sample size is at most 10% of the population size when sampling without replacement.
Check your recall[13 marks]
6 written questions. Answer each one in your head or on paper, then open the mark scheme.
- 1.Calculate[3 marks]
The population proportion is . Calculate the mean and standard deviation of the sampling distribution of for random samples of size 200.
Show mark schemeHide mark scheme
Model answer
The mean is . The standard deviation is .
- 1 mark for stating that the mean is 0.30
- 1 mark for substituting into
- 1 mark for obtaining a standard deviation of about 0.0324
- 2.Describe[2 marks]
Describe the shape of the sampling distribution of when and .
Show mark schemeHide mark scheme
Model answer
It is approximately normal. The large counts condition holds, since and are both at least 10.
- 1 mark for stating that the shape is approximately normal
- 1 mark for supporting this with the large counts condition and the values 50 and 50
- 3.Justify[3 marks]
A random sample of 50 is taken from a very large population in which . Justify whether a normal model for is appropriate.
Show mark schemeHide mark scheme
Model answer
It is not appropriate. Here , which is less than 10, so the large counts condition fails. The distribution is likely skewed to the right.
- 1 mark for concluding that the normal model is not appropriate
- 1 mark for calculating
- 1 mark for stating that 3 is less than 10, so the large counts condition fails
- 4.Predict[2 marks]
The standard deviation of is 0.04 for samples of size 100. Predict its value for samples of size 400 from the same population.
Show mark schemeHide mark scheme
Model answer
It will be 0.02. The sample size is multiplied by 4, so the standard deviation is divided by .
- 1 mark for predicting a standard deviation of 0.02
- 1 mark for linking this to dividing by the square root of 4
- 5.Identify[1 mark]
Identify the name of the condition that requires and .
Show mark schemeHide mark scheme
Model answer
It is the large counts condition.
- 1 mark for identifying the large counts condition
- 6.Explain[2 marks]
Explain why the 10% condition is checked when a random sample is taken without replacement.
Show mark schemeHide mark scheme
Model answer
Sampling without replacement makes later selections slightly dependent on earlier ones. When the sample is at most 10% of the population, this effect is negligible and the formula for the standard deviation still applies.
- 1 mark for stating that sampling without replacement makes selections slightly dependent
- 1 mark for explaining that a sample of at most 10% of the population makes the effect negligible

Practice this topic
9 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 9 answered
Includes the 2 quick checks in the note above.
EasyCalculate[1 mark]
Show answer and explanation
Answer: D · Worked explanation
MediumDetermine[1 mark]
Show answer and explanation
Answer: D · Worked explanation
MediumDetermine[1 mark]
Show answer and explanation
Answer: B · Worked explanation
MediumIdentify[1 mark]
Show answer and explanation
Answer: D · Worked explanation
HardCalculate[2 marks]
Show answer and explanation
Answer: B · Worked explanation
HardDetermine[2 marks]
Show answer and explanation
Answer: D · Worked explanation
HardDetermine[2 marks]
Show answer and explanation
Answer: A · Worked explanation