CHAPTER 5: DATA COLLECTION AND SAMPLING
TRUE/FALSE
1. An observational study involves collecting data about persons or objects by recording information
about their selected characteristics of interest.
2. Self-administered surveys usually have a high response rate.
3. In designing a survey, demographic questions must be avoided.
4. The response rate of a survey is the proportion of all people who were selected but did not complete
the survey.
5. A self-selected sample is the group of individuals who were randomly selected to be in the sample,
then agreed to participate in the study.
6. Experimental data tend to be more reliable, or “stronger,” than survey data.
7. An experiment involves collecting data about persons or objects by deliberately exposing them to
some kind of change and comparing the results.
8. A question on a survey that was not answered is an example of an open-ended question.
9. A self-selected sample is one in which the individuals choose themselves to be in the sample.
10. “Wouldn’t you agree that foreign cars are better than American cars?” is an example of a well-worded
survey question.
MULTIPLE CHOICE
1. Which method of data collection is involved when a researcher counts and records the number of
students wearing backpacks on campus in a given day?
a.
An experiment.
c.
Direct observation.
b.
A survey.
d.
None of these choices.
2. Which of the following statements is true regarding the design of a good survey?
a.
The questions should be kept as short as possible.
b.
A mixture of dichotomous, multiple-choice, and open-ended questions may be used.
c.
Leading questions must be avoided.
d.
All of these choices are true.
3. A marketing research firm selects a random sample of adults and asks them a list of questions
regarding their beverage preferences. What type of data collection is involved here?
a.
An experiment.
c.
Direct observation.
b.
A survey.
d.
None of these choices.
4. Which of the following must be avoided in designing a survey?
a.
Dichotomous questions.
c.
Demographic questions.
b.
Leading questions.
d.
All of these choices are true.
5. A researcher conducts a study where she divides subjects into two groups, gives each group a certain
treatment, and records their responses. What type of data collection is being used here?
a.
An experiment.
c.
A survey.
b.
Direct observation.
d.
A census.
6. The personnel director at a large company studied the eating habits of the company’s employees. The
director watched and recorded whether each employee brought his/her own lunch to work, ate at the
company cafeteria, or went out to lunch. What method of data collection was used here?
a.
Direct observation.
c.
A survey.
b.
An experiment.
d.
A personal interview.
7. Which of the following data collection methods is not observational?
a.
A personal interview.
c.
A self-administered questionnaire.
b.
A telephone interview.
d.
An experiment.
COMPLETION
1. In a(n) ____________________ study, there is no attempt to control factors that might influence the
variable of interest.
2. The ____________________ rate is the proportion of people in the sample who completed the survey.
3. In a(n) ____________________ study, individuals are randomly assigned to different treatments and
the results are compared.
4. A survey is an example of a(n) ____________________ study.
5. Two types of interviews that are used to collect data are ____________________ interviews and
____________________ interviews.
6. In a self-administered survey, the individuals in the sample are typically contacted by
____________________.
7. Gender, occupation, and age are all examples of ____________________ variables.
SHORT ANSWER
1. Describe the difference between an observational study and an experimental study.
2. Briefly discuss three methods of conducting a survey of people.
3. Give three important points to consider when designing a questionnaire.
4. List one advantage and one disadvantage of a telephone interview as a method of data collection.
5. List one advantage and one disadvantage of a personal interview as a method of data collection.
6. Discuss one advantage and one disadvantage of a self-administered survey as a method of data
collection.
Soft Drinks
A soft drink manufacturer has been supplying its products in bottles to grocery stores and in cans to
small convenience stores. The company is analyzing sales of this product to determine which type of
packaging is preferred by customers.
7. {Soft Drink Narrative} Is this study observational or experimental? Explain.
8. {Soft Drink Narrative} Outline a better method for designing this study, so the same types of stores
don’t get the same types of packaging.
Smoking and Heart Attacks
A medical researcher is interested in investigating the relationship between smoking and heart attacks
9. {Smoking and Heart Attacks Narrative} Briefly describe how the researcher might design an
observational study to investigate the relationship between smoking and heart attacks
10. {Smoking and Heart Attacks Narrative} What type of studies are plausible in this particular scenario,
observational studies or experiments?
11. {Smoking and Heart Attacks Narrative} How can you show that smoking causes heart attacks without
being able to do a designed experiment?
12. A person receives a mail survey and shreds it without opening it. This causes nonresponse error.
13. Self-selected samples have no bias because they are chosen by the people themselves.
14. A cluster sample occurs when you randomly select groups, and for each group selected, you sample
every single member of that group.
15. The larger the sample size is, the more accurate we can expect our sample estimates to be.
16. Selection bias occurs when researchers select biased questions to include on a survey.
17. The target population is the population about which we want to draw inferences and conclusions,
while the sampled population is the actual population from which the sample has been taken.
18. A target population and a sampled population mean the same thing.
19. A self-selected sample represents the sampled population but not the target population.
20. A nonsampling error can be caused by the wording of a question.
21. When responses are not obtained from some members of the sample, bias is introduced.
22. A sampling error can be reduced by taking a larger sample size.
23. Sampling error refers to the difference between the sample and the population that exists only because
of the observations that happened to be selected for the sample.
24. Sampling error is the result of a mistake made during the sampling process.
25. Cluster samples typically cost less but they also increase sampling error.
26. A simple random sample is chosen in such a fashion that every possible subset of the same size has an
equal chance of being selected.
27. Nonresponse error occurs when responses are not obtained from some members of the sample.
28. Nonresponse error occurs when someone was not selected to participate in the survey.
29. Selection bias is a systematic tendency to favor including individuals with particular characteristics,
while excluding individuals with other characteristics.
30. To reduce sampling error, minimize the chance for bias to occur during sampling.
31. When every possible sample with the same number of observations is equally likely to be chosen, the
result is called a:
a.
simple random sample.
b.
stratified random sample.
c.
cluster sample.
d.
biased sample.
32. The manager of the customer service division of a major consumer electronics company is interested
in determining whether the customers who have purchased a videocassette recorder over the past 12
months are satisfied with their products. If there are 4 different brands of videocassette recorders made
by the company, the best sampling strategy would be to use a:
a.
simple random sample.
b.
stratified random sample.
c.
cluster sample.
d.
self-selected sample.
33. Which of the following causes sampling error?
a.
Taking a random sample from a population instead of studying the entire population.
b.
Making a mistake in the process of collecting the data.
c.
Nonresponse bias.
d.
All of these choices are true.
34. A pharmaceutical company interested in measuring how often physicians prescribe a certain drug has
selected a simple random sample from each of two groups: M.D. (Medical Doctors) and D.O.
(Osteopaths). What is this type of sampling called?
a.
Simple random sampling.
b.
Cluster sampling.
c.
Stratified random sampling.
d.
None of these choices.
35. When the population is divided into mutually exclusive sets, and then a simple random sample is
drawn from each set, this is called:
a.
simple random sampling.
b.
stratified random sampling.
c.
cluster sampling.
d.
selection bias.
36. Which of the following types of samples is almost always biased?
a.
Simple random samples.
b.
Stratified random samples.
c.
Cluster samples.
d.
Self-selected samples.
37. The difference between a sample mean and the population mean is called:
a.
nonresponse error.
b.
selection bias.
c.
sampling error.
d.
nonsampling error.
38. Which of the following types of samples should not be used to make good statistical inferences from a
sample to a population?
a.
Stratified random samples.
b.
Self-selected samples.
c.
Cluster samples.
d.
All of these choices are true.
39. Which of the following is an example of a nonsampling error?
a.
Some incorrect responses are recorded.
b.
Responses are not obtained from all members of the sample.
c.
Some members of the target population cannot possibly be selected for the sample.
d.
All of these choices are true.
40. The Admissions Officer from a large university mailed a survey to 600 students selected at random.
The sample was designed to include 150 students randomly selected from each of the freshman,
sophomore, junior, and senior classes on campus. What sampling method was used?
a.
Simple random sample
b.
Systematic sample
c.
Stratified random sample
d.
Cluster sample
41. Which of the following situations lends itself to cluster samples?
a.
When it is difficult to develop a complete list of the population members.
b.
When the population members are widely dispersed.
c.
When selecting and collecting data from a simple random sample is too costly.
d.
All of these choices are true.
42. To give away a door prize, the hostess of a Tupperware party put each person’s name into a hat, mixed
them up, and selected one name. What sampling method was used?
a.
Simple random sample
b.
Systematic sample
c.
Stratified random sample
d.
Cluster sample
43. Which of the following describes selection bias?
a.
A leading question is selected for inclusion in the survey.
b.
Some members of the target population are excluded from possible selection for the
sample.
c.
A person selected for the sample has a biased opinion about the survey.
d.
All of these choices are true.
44. Proper interviewer training helps to reduce ____________________ error.
45. Excluding some members of the target population results in ____________________ bias.
46. ____________________ error results from the failure to collect data from all subjects in the sample.
47. ____________________ error refers to differences between the sample and the population.
48. ____________________ error is due to mistakes made in the acquisition of data.
49. A(n) ____________________ sample is obtained by separating the population into groups and taking
a simple random sample from each group.
50. ____________________ sampling is particularly useful when it is difficult or costly to develop a
complete list of the population members.
51. What is meant by a self-selected sample? Why are self-selected samples not desirable?
52. A senator wants to estimate the mean age of registered voters in her state. Unfortunately, she does not
have a complete list of households in her state. Describe a sampling plan that would be suitable for her
purposes.
53. The Chairman of a College of Business with five departments wants to estimate the average number of
student-hours lost per month due to illness of their professors. Describe a sampling plan that will help
the Dean compare the average student-loss hours for the five departments.
54. Briefly describe three types of nonsampling errors.
55. Pollsters want to know what percentage of all registered voters in Missoula, Montana, intend to vote in
the next election. They visit with 350 people at the downtown shopping mall during one afternoon and
ask each person whether or not they intend to vote. Are the target population and the sampled
population the same in this case? Explain.
56. Give an example of a poll that involves a self-selected sample.
57. Is it possible for a sample to yield better results than a census, from a practical standpoint? Explain.
58. A regular feature in many newspapers asks readers to respond via e-mail to a survey question. The
percentages of yes and no responses are usually reported the following day. Should we ignore the
results of these surveys? Explain.