Integrated Math 3 / Unit 8: Statistics and Inference
8.4 Surveys, Observational Studies and Experiments
Notes
- A survey asks questions of a sample. Wording and order can cause bias.
- An observational study observes without assigning treatments. It can show an association but not a cause.
- An experiment randomly assigns subjects to treatments. A control group gets no treatment or a placebo for comparison.
- Random sampling lets you generalize to the population. Random assignment lets you conclude cause and effect.
Practice
Researchers randomly assign 100 students to two groups. One group follows a new sleep schedule and the other keeps its usual schedule. Then they compare test scores. This is:
The researchers assigned the treatment (the sleep schedule) at random.
A study records the sleep hours and grades of 200 students and finds that students who sleep more have higher grades. What conclusion is justified?
Observational studies do not control other factors, such as study habits, that could explain the link.
What is the main purpose of random assignment in an experiment?
Random assignment balances other factors across groups, which supports cause-and-effect conclusions.
Ready for more? Take the Unit 8 test.