Math · Problem-Solving and Data Analysis

Inference from Sample Statistics and Margin of Error on the Digital SAT

Many of these questions read like careful reasoning about a study. A researcher measures a random sample, reports a statistic and a margin of error, and the SAT asks which conclusion is reasonable, so the answer choices are sentences and exactly one respects what a sample can and cannot tell you. The easier items lean on that reasoning, but the harder ones are genuinely computational: you estimate a population total from a sample, scale a percentage and its margin to a count range, or use how the margin of error shrinks as the sample grows. Expect to both interpret and calculate.

This skill is low-volume: expect one question, maybe two, per test. But it is nearly pure logic, and students routinely lose the point simply because they have never seen the format. Nobody teaches "margin of error interpretation" in most math classes, so the first time many students meet it is on test day. Reading this page once is most of the fix.

Two ideas carry everything. First, a statistic from a random sample is the best estimate of the same statistic for the whole population. Second, the margin of error builds a plausible range around that estimate for the population value, not for any individual person, and it never guarantees the true value sits inside the range.

New to the Digital SAT? Start with how the test is structured and scored.

What the SAT actually tests

Sample-to-population inference: the mean or percent from a random sample is the best estimate of the mean or percent for the population the sample was drawn from.
Interpreting margin of error as a plausible range for the population value. An estimate of 62% with a margin of error of 4% means the population percent is plausibly between 58% and 66%.
What margin of error does NOT mean: it says nothing about individuals, it does not measure mistakes in responses, and it does not make the estimate exact.
Keeping the population straight: a sample of one city's adults supports conclusions about that city's adults, not the whole country.
How sample size affects margin of error: larger random samples produce smaller margins of error, so estimates get tighter, not more "correct."
Reasoning with the interval: if a plausible range like 49% to 59% includes values below 50%, the data does not establish a majority.

Strategies that work

Build the interval immediately

The moment you see "margin of error," compute estimate minus margin and estimate plus margin, and write the range down. Almost every correct answer is a careful sentence about that range, and every trap is a sentence that ignores it or overstates it.

Know the two estimating moves

For a percentage, multiply the sample proportion by the population to estimate a count. For a per-unit average, multiply the sample mean by the total number of units to estimate a total. Most harder questions start with one of these before any interpretation.

Match the population to the sample

Underline who was actually sampled: students at one school, adults in one city, likely voters. The conclusion can only reach as far as that group. Any answer choice that quietly upgrades the population, from one school to all schools, is wrong no matter how reasonable it sounds.

Hunt for absolute words

Words like "exactly," "all," "every," "must," and "certain" almost always mark a wrong answer, because sample data supports plausible conclusions, not guarantees. The correct choice usually says "plausible," "likely," "estimated," or "between."

Test the majority claim against the interval

When a question involves support above or below 50%, check whether the entire interval clears the line. An estimate of 54% with a margin of error of 5% spans 49% to 59%, so a value below half is still plausible and no majority is established.

Mistakes to avoid

Thinking margin of error describes individuals, for example "every student sleeps between 6.8 and 7.4 hours." The interval is about the population average, not any one person.
Treating the sample statistic as exact for the population: "exactly 62% of city adults support the plan" is never a supported conclusion.
Generalizing past the sampled population, like applying one school's survey to all US students.
Believing the true population value must fall inside the interval. The interval is plausible, not guaranteed.
Assuming a bigger sample changes the answer rather than the precision. More data shrinks the margin of error; it does not make a biased sample trustworthy.

Practice with Nova, your Math coach

Answer right here and Nova walks you through it, just like in a drill. Difficulty labels are relative within this skill.

Tip: the Calculator button on each question opens the same Desmos graphing calculator you get on the real Digital SAT. Try solving these with it.

Question 1Easy

A researcher selected a random sample of 100 students from the 2,400 students enrolled at a large high school. The mean amount of sleep on school nights for the students in the sample was 7.1 hours.

Based on the sample, which of the following is the best estimate of the mean amount of sleep on school nights for all 2,400 students at the school?

Pick an answer to get instant coaching from Nova.

Question 2Medium

A polling organization surveyed a random sample of 500 adults living in a city. In the sample, 62% of the adults supported building a new public park, with an associated margin of error of 4%.

Which of the following is the most appropriate conclusion based on the survey?

Pick an answer to get instant coaching from Nova.

Question 3Hard

A news outlet polled a random sample of likely voters in an upcoming two-candidate election. In the sample, 54% of the voters supported Candidate A, with an associated margin of error of 5%.

Which of the following statements is best supported by the results of the poll?

Pick an answer to get instant coaching from Nova.

Keep missing Inference from Sample Statistics and Margin of Error questions?

SAT Prep Quest tracks your level on this skill (and the other 27), then feeds you 5-minute drills right at your challenge zone until it is fixed.

Drill this skill free

The rest of Problem-Solving and Data Analysis

Inference from Sample Statistics and Margin of Error is one of 7 skills in Problem-Solving and Data Analysis. The ideas build on each other, so it pays to learn them as a set rather than in isolation. See how Problem-Solving and Data Analysis fits together.

SAT is a registered trademark of the College Board, which was not involved in producing, and does not endorse, this product. Score estimates are Learner Labs projections, not official College Board scores.