Research Methods Probability Sampling Identify possible sources of bias in each survey: Customers at a supermarket are sampled to determine their opinion about a controversial political issue.
Television viewers are invited to call an 800 number to report their opposition to a bill to increase state gasoline taxes. A large company selects names from a telephone book to sample for a survey on household spending habits.
Administrators at a local hospital want to determine which activity employees would most enjoy as an annual event: a family picnic, an employee golf outing, a dance, or a day at the races. The administrators have one week to survey employees and gather the input it needs to make a decision. Because XYZ Hospital has over 2,000 employees, contacting each employee is not feasible, so the administrators agree to contact a sample of employees.
- Several administrators have ideas on how to gather this information. Consider each of the following suggestions. Comment on the advantages and disadvantages of each method.
- Jane suggests that the eight administrators should vote on which activity is most favorable.
- Bill suggests that each member ask 15 hospital acquaintances which activity they prefer. Therefore, 120 employees would be sampled.
- Choi suggests placing a suggestion box in the cafeteria so that any employee can participate in the sample.
- Juan thinks that the administrators should select several nursing supervisors at random and survey nurses on their unit.
- Chantal knows that the computer in the main office can select employees at random who can be included in the sample.
- Describe a different method that could be used to generate a sample of XYZ Hospital employees to vote on which activity they prefer. Use what you know about sampling to justify your answer.
- For each of the following sample methods, identify the groups in the population that are underrepresented.
- To obtain a sample of households, a computer reporter dials numbers taken at random from a telephone directory.
- A pharmaceutical manufacturer wishes to survey a sample of physicians, so s/he randomly selects the names of physicians from a medical society list.
- A college professor wants to know what percentage of young adults, ages 18-22, consider education a top priority. S/he obtains a list of all students on campus from the registrar and randomly selects names from the list.
- A radio station wishes to examine the proportion of its listeners who voted in the last presidential election. They conduct a poll by asking listeners to call the station.