SAT Math · Problem-Solving and Data Analysis · Skill 7 of 7

Evaluating statistical claims

Read how a study was run and decide what it can prove. Two questions do almost all the work: were the treatments randomly assigned, and were the people randomly chosen?

9 chapters plus a challengeAbout 35 minutesFree, no sign-up
Start with the grid →Jump to the challenge
Hi, I’m Io. Headlines love the word “causes”. By the end of this lesson you will know when a study has earned it.
Tap Io

What can this study conclude?

Explore · 5 min

Researchers want to know whether a new study app raises test scores at a large high school. How they choose students and how they decide who uses the app changes what they are allowed to claim. Try all four designs.

Observational studies and experiments

Sort · 4 min

  • Experiment: the researchers assign a treatment, then measure the result
  • Observational study: the researchers only record what people already do, for example with a survey

Random assignment and cause and effect

Learn · 4 min

When people choose their own group, the groups can differ in many ways: motivation, health, money, habits. Random assignment spreads those differences evenly, so a difference in results can be put down to the treatment.

random assignment → cause and effect

Random selection and who the results fit

Learn · 4 min

If participants were chosen at random from a population, the results apply to that population. If they volunteered or were easy to reach, the results apply only to people like those in the study.

random selection → applies to the population sampled

Confounding variables

Learn · 4 min

A confounding variable is a hidden third factor linked to both things being compared. It can make two things look connected when neither causes the other. Random assignment is what protects an experiment from them.

Classic exampleIce cream sales and swimming accidents rise together. Ice cream does not cause accidents. Hot weather drives both.

Choosing the best-supported claim

Practise · 4 min

SAT answer choices often differ by just a few words. Check two things in each choice: does it claim cause or only an association, and which group does it talk about?

  • No random assignment: use “is associated with” or “is linked to”
  • Random assignment: “causes” or “leads to” is allowed
  • Match the group to how participants were chosen

Judge the study

Practise · 5 min

Read each study, then answer the two questions. A new study appears each time.

Claims in real life

Scenarios · 6 min

Each tab is a situation you could meet on test day. Answer every question to finish the chapter.

Spot the trap

Detective · 3 min

Each case has one faulty step. All three slips appear as wrong answer choices on the SAT.

Final challenge

8 questions · 8 min

Key ideas to carry in
ExperimentResearchers assign the treatment.
ObservationalResearchers only record what happens.
Random assignmentNeeded to claim cause and effect.
Random selectionNeeded to apply results to a population.
ConfoundingA third factor can drive both.
Best claimRight strength of wording, right group.
Challenge