HardStatistics & Data ScienceHigh School (9–10)High School (11–12)UndergraduateGeneralStatistics Basics › Study Design and ExperimentsStatistics Basics › Data and SamplingConceptual
A made-up headline says: "Breakfast eaters are slimmer! …
Contributed by StemPy LabTry it on paper first. A hint, the key idea and the worked solution are here when you need them.
A made-up headline says: "Breakfast eaters are slimmer! A study of 5000 adults finds that people who eat breakfast every day weigh less on average than people who skip it." Read the claim as a statistician. Say what kind of study it probably was, name two possible confounding variables, give one reverse-cause explanation, and describe a study that could test for a cause.
Need a reminder? The key ideaShow
A confounding variable is linked to both the explanatory and the response variable. Compare like with like inside groups, or assign at random. A relative rise of on a risk of per 1000 adds people per 1000.
The worked solution
Have you tried it?
Work it out on paper first. It is fine to get stuck or make a mistake: that is how we learn. When you are ready, go through the solution one step at a time, and check each step against your own.
Step 1. The kind of study. Probably an observational study: the adults already ate breakfast or did not. It shows a link, not a cause.
Step 2. Confounders. People who eat breakfast may also exercise more, or sleep more regular hours. Either could lower weight, and either goes with breakfast.
Step 3. Reverse cause. People who are trying to lose weight sometimes skip breakfast. Then being heavier leads to skipping breakfast, not the other way round.
Step 4. A test for a cause. Take volunteers who do not usually eat breakfast. Use random assignment to make two groups. One group eats a set breakfast every day and the other does not, for some months. Compare the change in weight, in kg, between the groups.
Answer: an observational link, with exercise and sleep as possible confounders and dieting as a reverse cause. Only a randomised experiment can test whether breakfast itself makes a difference.
Discussion (0)
Log in to join the discussion.
Loading…