Back to Chapter 8 Menu

Back to Research design explained home page

 

 

CHAPTER 8 EXERCISES:

 ANSWERS AND HELPFUL HINTS

1. Obviously, the answers to 1a.1b, and the first part of 1c will depend on your experience. To answer the last part of 1c ("Do you think they made the right choice? Why or why not?"), you will probably want to review  Table 8.3 (it is on pp. 294-295) and pages 290-291 (specifically, read these three sections: "Written Instruments: A Summary," "Advantages of Interviews," and "Two Methodological Disadvantages of Interviews").

2. You will need to come up with the topic on your own. If you are having trouble, think about some problem that seems to be common among your friends or on your campus (or re-read pages 281-283). Remember, however, not to choose a hypothesis that a survey cannot test (pages 281-284 explain what types of hypotheses cannot be tested using a survey (e.g., cause-effect hypotheses).

 

3. To answer this question, review  Table 8.3 (it is on pp. 294-295) and pages 290-291 (specifically, read these three sections: "Written Instruments: A Summary," "Advantages of Interviews," and "Two Methodological Disadvantages of Interviews").

 

4.

Question

Format

 

Advantages

 

Disadvantages

Nominal-

dichotomous

• Easy to answer

• Easily and objectively

  scored

• High reliability

• Participants  may dislike

• Participants’ viewpoints may not be represented

• Provides only ordinal data

• Deprives study of power because (1) measure is insensitive and (2) may require use of less powerful statistical techniques.

Likert-type

• Easy to answer

• Easily and objectively  scored

• High reliability

• Sensitive

• Provide interval data

• Can be analyzed with powerful statistical tests

• Potential for summating scores

• Participants

  may resist

  fixed-response

  format

Open-ended

• Allows participants freedom to respond as they choose

• Good for exploratory research

• Time-consuming to answer

• Time-consuming to score

• Hard to score objectively.

 

5. The questions you write will depend on your hypothesis. Just be sure they are nominal-dichotomous (usually yes-no questions) and that they help you answer your research question. For more about what kinds of nominal-dichotomous questions you could ask--and why you might want to ask those kinds of questions--see pages 297-298.

6. The questions you write will depend on your hypothesis. Just be sure they are Likert questions (Likert questions usually  ask you to either strongly agree, agree, neither agree nor disagree, disagree, or strongly disagree with a statement) and that your Likdert questions help you answer your research question. For more about what kinds of Likert you could ask--and why you might want to ask those kinds of questions--see pages 298-299.

7. A Gallup/CNN poll asked, “How likely do you think it is that Democrats in the Senate would attempt to block Bush’s nominee for inappropriate political reasons.Which two of this chapter’s nine tips for writing questions did this question violate?

The tips are listed and described on pages 303-305. However, the two tips that this question violates are both on page 303.

 Rewrite the question to improve its validity.

            Just use the two key tips you found.

8. A former president of the Association for Psychological Science wrote, “sampling ain’t simple” (Gernsbacher, 2007, p. 13). Explain why that is a true statement.

Defining the population is often not easy. For example, how would you define the population of “voters in the next election”? Once you define the population, contacting a random sample of those people might not be easy. Finally, not everyone you contact will be willing to complete the survey.

What questions would you ask of a sample to determine how much to trust that sample?

What was their intended population? How did they define it? Did they take a reasonably large random sample of that population? Of the people they contacted, what percentage completed the study?

            9.          Why can you make statistical inferences from data obtained from a random sample?

Hints: Inferential statistics can be used to make inferences from a sample to a population as long as the assumptions of the statistical tests are met. What is the assumption made by these tests about the reason a sample may differ from its population? How do both random sampling and stratified random sampling set up conditions that  consistent with that assumption?

            10.        Why might having participants sign informed consent statements (a statement that they had been informed of the nature of the study, the risks and benefits of the study, the participants’ right to refuse to be in the study, the participants’ right to quit the survey at any point, and the participants’ right to confidentiality) make a survey research study less ethical? (Hints: Under what circumstances does the APA ethical code not require informed consent for surveys [see Appendix D]? Under what circumstances would requiring informed consent reduce the value of the survey without providing any benefits to participants?)

If the survey is anonymous, innocuous, and doesn’t elicit sensitive information from participants, informed consent is not required. Filling out the informed consent form might make the study less ethical by making the participants’ involvement in the study less confidential and more time-consuming without providing any benefits to the participant.

 


Back to Chapter 8 Menu

Back to Research design explained home page