Survey Research

Surveys are popular, because they are efficient; researchers can gather a great deal of information for a small cost and generally in a short amount of time. To consider whether surveys are a good idea for your study, consider these issues (from Vogt, Gardner & Haeffele (2012).

1. The data are best obtained directly from the respondents

2. Your data can be obtained by brief answers to structured questions.

3. You can expect respondents to give you reliable information.

4. You know how you will use the answers.

5. You can expect an adequate response rate.

Now let us consider each of these issues.

1. The data are best obtained directly from the respondents.

Often the only way to obtain information about people is by asking them. This is especially true of subjective data, i.e., the inner states of the subjects being studied, such as attitudes, beliefs, or values. You can also use surveys to collect objective data, such as respondents' age, income, or years of work experience, which could be obtained in other ways, but it is usually easier simply to ask. However, if you have access to records, such as educational and medical records, these may be more accurate and possibly more efficient than asking individuals. People's memories are notoriously poor on such questions, as "how often have you visited your doctor in the past year." Having access to their records would make it much more accurate. Keep in mind that asking unimportant or needless questions tend to annoy participants and they may quit your study because of it.

2. Your data can be obtained by brief answers to structured questions.

Surveys work best when asking structured questions. Structure refers to the degree of control you want to exercise over the answers you will get. The questions may be either completely unstructured and vague or highly structured. The more structured the questions, the more participants are constrained to your predetermined answers. Therefore, you may be limiting their responses; they may have other things to say. On the other hand, having broad and exploratory questions as in interviews, may not be the best choice for surveys, as the data may not be able to be summarized.

3. You can expect respondents to give you reliable information.

Sometimes surveys are an unwise choice because respondents may find it difficult to answer accurately or truthfully. Perhaps the information you seek is hard to remember or too sensitive for people to be willing to reveal it to a stranger. It is often assumed that social desirability biases much survey research, meaning that respondents may answer questions to reflect what they think is socially appropriate rather than what they really believe or do. Racial beliefs and attitudes provide an example of this. An example given by Vogt et al. (2012) is in the second half of the 20th century, the number of people answering national surveys in ways indicating they held a racial prejudice dropped rapidly compared to earlier surveys. Whether people were less prejudiced in the 1990s than in the 1950s is uncertain. However, it is clear that the behavior of respondents on the same survey questions dramatically changed.

Next time we will continue our discussion of surveys. Do you have an issue or a question that you would like me to discuss in a future post? Would you like to be a guest writer? Send me your ideas! leann.stadtlander@waldenu.edu