A scientist takes a big bucket of water from a lake and counts how many species of bacteria, bugs, and other creepy crawlies he finds in the bucket. Identify the population, the sample, the parameter, and the estimate in this situation.
Hint
How can we determine how many species are in this lake?
Answer
The population is "all the species that live in the lake." The sample is "the species that are in the bucket." The parameter is the number of species in the lake, while the estimate is the number of species found in the bucket.
Example 2
A school takes a poll to find out what students want to eat at lunch. 70 students are randomly chosen to answer the poll questions. What are the population, the sample, the parameter, and the estimate of this study?
Hint
A sample is a subset of a population, while an estimate tries to, uh, estimate a parameter.
Answer
The population is all the students at the school, and the parameter is the lunch preferences of the whole school. The sample is the 70 students polled, and their responses to the poll are the estimate.
Example 3
When is it okay to NOT use random sampling?
Hint
Random sampling is what us allows us to make estimates from a sample that are representative of the population.
Answer
We always want to use random sampling. We're BFFs. Sometimes we can't, though, like when running an observational study. When we don't have random sampling, we have to be more cautious in interpreting our results, because our sample won't be representative of the full population.
Example 4
You want to know what proportion of people enjoys getting a root canal. What type of study should be done?
Hint
We
want an estimate of the proportion of a larger population.
Answer
A sample survey
Example 5
What does it mean for an experiment to be double blind?
Hint
While we like the mental image it gives us, it does not mean that everyone in the experiment is wearing two blindfolds. It does have to do with who can "see" which individuals are in the control and experimental groups.
Answer
Neither the researchers nor the individuals being studied know who is in the control and experimental groups. This reduces bias from people changing their behavior based on which group they are dealing with.