Inference & Margin of Error – SAT Math

📖 What Are Inference and Margin of Error?

Statistical inference is the process of using data from a sample to make conclusions about a larger population. The margin of error tells us how much the sample results might differ from the true population value.

Population

The entire group being studied.

All voters in the US

Sample

A subset of the population selected for study.

1,000 randomly selected voters

Margin of Error

The range around the sample statistic where the true population value likely falls.

\(\pm 3\%\)

Confidence Interval

Sample statistic ± margin of error.

\(52\% \pm 3\%\) = (49%, 55%)

1. Margin of Error

📌 RULE: Margin of Error

The margin of error (MOE) tells us how much the sample estimate might differ from the true population value.

\[ \text{Confidence Interval} = \text{Sample Statistic} \pm \text{Margin of Error} \]

Key Facts:
• Larger sample size → smaller margin of error
• Smaller sample size → larger margin of error
• The margin of error decreases as the sample size increases

💡 Strategy — Margin of Error

1. Identify the sample statistic (percentage or mean).
2. Identify the margin of error.
3. Calculate the confidence interval: statistic ± MOE.
4. The true population value is likely within this range.

📝 SOLVED EXAMPLE 1 — Margin of Error

A survey of 500 randomly selected voters found that 52% support a new policy, with a margin of error of ±3%. What is the confidence interval?

Step 1: Sample statistic = 52%

Step 2: Margin of error = 3%

Step 3: Lower bound = 52% − 3% = 49%

Step 4: Upper bound = 52% + 3% = 55%

✅ Confidence Interval: (49%, 55%)

💡 Tip: We can be confident that the true population value is between 49% and 55%.

2. Sample Size and Margin of Error

📌 RULE: Sample Size Effect

Larger sample size → Smaller margin of error (more precise estimate)
Smaller sample size → Larger margin of error (less precise estimate)

Example: A survey of 1,000 people has a smaller margin of error than a survey of 100 people.

📌 Key Concept

Random sampling is important! A random sample is more likely to represent the population. A biased sample will have systematic errors.

📝 SOLVED EXAMPLE 2 — Sample Size

Which survey would have a smaller margin of error: one with 200 participants or one with 2,000 participants?

Step 1: Larger sample size = smaller margin of error

Step 2: 2,000 participants is larger than 200

Step 3: The survey with 2,000 participants has a smaller margin of error

✅ The survey with 2,000 participants has a smaller margin of error

💡 Tip: More data = more confidence in the results.

3. Interpreting Results

📌 RULE: Making Inferences

When interpreting survey results, remember:

✅ Good: "We are 95% confident that the true proportion is between X% and Y%"

❌ Bad: "Exactly X% of the population believes..." (unless we surveyed the entire population)

📝 SOLVED EXAMPLE 3 — Interpretation

A poll finds that 45% of students prefer online learning, with a margin of error of ±4%. Which statement is correct?

Step 1: Confidence interval = 45% ± 4% = (41%, 49%)

Step 2: We are confident the true percentage is between 41% and 49%

Step 3: It would be incorrect to say exactly 45% of all students prefer online learning

✅ The true percentage is likely between 41% and 49%

💡 Tip: Avoid making absolute claims about the population from sample data.

4. Confidence Intervals

📌 RULE: Confidence Interval

The confidence interval is the range of values that is likely to contain the true population parameter.

\[ \text{Confidence Interval} = \text{Sample Statistic} \pm \text{Margin of Error} \]

Example: 45% ± 4% = (41%, 49%)
Interpretation: We are confident that the true population value falls between 41% and 49%.

📝 SOLVED EXAMPLE 4 — Confidence Interval

A survey finds that 38% of people prefer coffee over tea, with a margin of error of ±5%. What is the confidence interval?

Step 1: Sample statistic = 38%

Step 2: Margin of error = 5%

Step 3: Lower bound = 38% − 5% = 33%

Step 4: Upper bound = 38% + 5% = 43%

✅ Confidence Interval: (33%, 43%)

💡 Tip: The true population value is likely between 33% and 43%.

🧪 Practice Questions

Solve each problem using the rules above. Click "Show Answer" to see the full solution.

Question 1

A survey found that 62% of people like chocolate, with a margin of error of ±4%. What is the confidence interval?

A) (58%, 66%)

B) (60%, 64%)

C) (58%, 66%)

D) (62%, 66%)

✓ Answer: C

62% ± 4% = (58%, 66%)

📝 Solution: 62 − 4 = 58, 62 + 4 = 66

Question 2

Which survey has a smaller margin of error?

A) Sample size = 1,000

B) Sample size = 100

C) Both have the same margin of error

D) Cannot be determined

✓ Answer: A

Larger sample size = smaller margin of error. 1,000 > 100.

📝 Solution: 1,000 participants → smaller MOE.

Question 3

A poll finds 55% support for a candidate with ±3% margin of error. Which is correct?

A) Exactly 55% of the population supports the candidate

B) The true support is 52%

C) The true support is 58%

D) The true support is likely between 52% and 58%

✓ Answer: D

55% ± 3% = (52%, 58%). The true value is likely in this range.

📝 Solution: (52%, 58%)

Question 4

A survey of 2,500 randomly selected voters found that 48% support a new law with a margin of error of ±2%. What is the confidence interval?

A) (46%, 50%)

B) (46%, 50%)

C) (48%, 50%)

D) (44%, 52%)

✓ Answer: B

48% ± 2% = (46%, 50%)

📝 Solution: 48 − 2 = 46, 48 + 2 = 50

Question 5

Which statement about margin of error is TRUE?

A) Larger sample size = larger margin of error

B) Margin of error is always 5%

C) Larger sample size = smaller margin of error

D) Sample size doesn't affect margin of error

✓ Answer: C

Larger sample size = smaller margin of error (more precise).

📝 Solution: Larger sample → smaller MOE.

Question 6

A survey with 500 participants has a margin of error of ±4%. What would happen to the margin of error if the sample size were increased to 2,000?

A) It would decrease

B) It would increase

C) It would stay the same

D) Cannot be determined

✓ Answer: A

Increasing sample size decreases the margin of error.

📝 Solution: Larger sample → smaller MOE.

Question 7

A poll finds that 35% of people prefer Brand A, with a margin of error of ±5%. Which could be the true population value?

A) 28%

B) 38%

C) 45%

D) 50%

✓ Answer: B

35% ± 5% = (30%, 40%). 38% is within this range.

📝 Solution: (30%, 40%) → 38% is possible.

Question 8

A survey of 1,200 randomly selected students found that 72% prefer in-person classes, with a margin of error of ±3%. What is the confidence interval?

A) (69%, 75%)

B) (70%, 74%)

C) (69%, 75%)

D) (72%, 75%)

✓ Answer: C

72% ± 3% = (69%, 75%)

📝 Solution: 72 − 3 = 69, 72 + 3 = 75

Question 9

A survey with a margin of error of ±2% is more precise than one with a margin of error of ±5%. Why?

A) Because it has a smaller sample

B) Because the range of values is narrower

C) Because it surveys more people

D) Because it is more random

✓ Answer: B

A smaller margin of error means a narrower range, which is more precise.

📝 Solution: Smaller MOE = narrower interval = more precise.

Question 10

A poll finds 44% support with ±4% margin of error. Which is NOT a possible value for the true population support?

A) 42%

B) 46%

C) 47%

D) 50%

✓ Answer: D

44% ± 4% = (40%, 48%). 50% is outside this range.

📝 Solution: (40%, 48%) → 50% is NOT possible.

🎉 WELL DONE!

You've completed the Inference & Margin of Error lesson. You now know how to interpret confidence intervals, understand the effect of sample size, and make inferences from sample data.

← Back to Topic List 📖 Previous: Probability & Conditional Probability 📖 Next: Evaluating Statistical Claims →