2.1 Data Collection
1. A large corporation wants to find out which benefits plan its employees would prefer. Which procedure would be most likely to obtain a statistically unbiased sample?
- Survey a random sample of employees from a list of all employees.
- Invite all employees to indicate their choices by e-mail.
- Place suggestion boxes at random locations in the company’s plant and offices.
- Assemble a group with one member from each department and record the preferences of these employees.
Survey a random sample of employees from a list of all employees.
2. A university polled 500 of its students, randomly selecting them proportional to the number of students enrolled in each degree program. Classify the sampling method.
- simple random
3. Which question is unbiased?
- Does the school board have the right to enforce a dress code?
- Do you think the mayor is doing a good job in spite of his questionable character?
- Do you prefer daytime or evening television programming?
- Do you think the government should be allowed to cut down trees willy-nilly to build a new highway?
Do you prefer daytime or evening television programming?
Spotting Problems with Sampling Methods
You should understand why samples should be representative and how to spot when they are not.
To spot a biased sample you should think about the following:
- Where, when and how the sample is taken.
- The sample size: large or small?