EasyStatistics & Data ScienceHigh School (9–10)High School (11–12)UndergraduateGeneralStatistics Basics › Data and SamplingConceptual
Name the kind of bias in each made-up study, and say which way the result is likely to be wrong…
Contributed by StemPy LabTry it on paper first. A hint, the key idea and the worked solution are here when you need them.
Name the kind of bias in each made-up study, and say which way the result is likely to be wrong.
- A sports website asks its readers, "How many hours of sport do you watch each week?"
- A survey of a city's eating habits phones the numbers in an old book of landline numbers.
- A student asks the first 30 people who leave a gym how often they exercise.
- A report looks at the 12 restaurants that have been open on a street for 20 years and finds that all of them serve large portions. It says that large portions keep a restaurant open.
Need a reminder? The key ideaShow
Bias is a slant in the way a sample is chosen. If of a population are easy to reach and the survey asks only them, it finds their view , while the truth is . The gap is the bias, in percentage points.
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, compare your working with the solution.
- Voluntary response. Readers of a sports website choose to answer, and keen sports fans answer most. The hours come out too high.
- Undercoverage. People with no landline, often younger people, cannot be chosen. The eating habits of those people are missing.
- Convenience sample. People leaving a gym exercise more than most. The result is too high.
- Survivorship bias. The restaurants that closed are not in the study. Many of them may also have served large portions, so the link may not exist at all.
Watch out. In each case the problem is the method. Asking more people in the same way would not fix it.
Discussion (0)
Log in to join the discussion.
Loading…