Chapter 7 Flashcards

1
Q

What is a survey?

A

A survey is a technique of data collection that is based on asking people questions about their beliefs, feelings etc. This is appropriate to use if your research question is about self-reported behaviours.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What are the phases of constructing a survey?

A

In the first phase, you develop an instrument that you use to measure variables.
Then you must conceptualise and operationalise all your variables as survey questions.
You will want to write and rewrite questions for clarity and completeness. In addition, you must organise questions on the questionnaire based on the research question, the respondents, and the type of survey.
You should also use pilot-tests.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What is a questionnaire?

A

In a questionnaire, the respondents read the questions themselves and mark answers themselves. It differs from a survey because it has introductory statements and instructions to add comfort and clarity and reduce potential errors.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What is an interview schedule?

A

In an interview schedule, an interviewer reads questions to the respondent and then records the respondent’s responses.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What type of language should one use when designing a questionnaire?

A

Language that is clear and precise. There should be no slang (only if the study requires it), no ambigous phrases and no double negations. This is all necessary so as to not confuse the respondent. Furthermore, neutral tone and language must be employed.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What is prestige bias?

A

Issues linked to people with high social status can nuance how respondents hear and answer survey questions. Avoid associating a statement with a prestigious person or group. Respondents may answer on the basis of their feelings toward the prestigious person or group rather than addressing the issue.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What are double-barreled questions?

A

A double-barreled question consists of two or more questions joined together. In order not to make the answer ambiguous, one should make each question about one and only one topic.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

What are leading questions?

A

A leading (or loaded) question is one that leads the respondent to choose one response over another by its wording. There are many kinds of leading questions (You don’t smoke, do you?). The respondent should not be aware of the answer that the researcher is seeking.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What are false premises?

A

When conducting a questionnaire the researcher may put forward a premise that might frustrate the respondent as they do not agree with it. One should always ask for a hypothetical situation.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

What types of questions are there?

A

Threatening, socially desirable, knowledge, skip (or contingency) questions, open and closed questions.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What are threatening questions?

A

Respondents may be reluctant to answer the questions at all, or to answer them completely and truthfully. If you wish to ask such questions, it requires great care and you must be extra cautious about the results. Threatening questions are part of a larger issue of self-presentation and ego protection. Respondents usually want to try to present a favourable image of themselves to other people.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What are socially desirable questions?

A

Social desirability bias is when respondents distort answers to make their reports conform to social norms. You can reduce social desirability bias by phrasing questions in ways that make norm conformity or violation appear to be less objectionable.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What are knowledge questions?

A

At times, you may want to learn whether respondents know about an issue or topic. Such questions can be threatening because respondents do not want to appear ignorant. They introduce recall bias which argues that participants do not always remember past events which will make them feel irritated during the study.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What are skip (or contingency) questions?

A

You want to avoid asking questions that are irrelevant for a respondent. Yet, some questions apply only to specific respondents. A contingency question is a two-(or more) part question. Contingency questions select respondents for whom a second question is relevant. On the basis of the answer to the first question, the respondent or an interviewer goes to another question or skips certain questions.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What are rating questions?

A

Rating questions ask the participant to rate different elements, such as the likelihood.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

What are ranking questions?

A

Ranking questions ask the participant to rank between some elements. However, if the participants feels like two or more elements are equal, he will necessarily have to rank them.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

What are agreement questions?

A

Agreement questions ask the participant whether they agree or disagree with a statement. This introduces acquiescence bias, the tendency to agree with statements, and dissent bias, the tendency to disagree with statements

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

What are reverse coded questions?

A

Reverse coded questions provide two or more statements aimed at detecting response set bias. For example, on a Likert scale you are initially asked “How happy are you today?” and you respond with Agree and then you are posed with the questions “How unhappy are you today?” and you respond with Agree, there is a response set bias. You are more likely to agree with the statements, no matter their contents.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

What are open-ended questions?

A

An open-ended (unstructured, free-response) question asks a question (e.g., “What is your favourite television program?”) to which respondents can give any answer.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

What are closed-ended questions?

A

A closed-ended (structured, fixed-response) question both asks a question and gives the respondent fixed responses from which to choose (e.g., “Is the president doing a very good, good, fair, or poor job, in your opinion?”).

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

What are some advantages and disadvantages for open-ended questions?

A

On one hand, open-ended questions permit an unlimited number of possible answers which allow the respondents to go into detail with their perspective. This helps answer questions about complex issues.
On the other hand, open-ended questions can contain a number of irrelevant detail that is hard to transcribe, process and analyse. Coding such answers will also be inefficient.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

What are some advantages and disadvantages for closed-ended questions?

A

On one hand, closed-ended questions are easier to code, analyse and compare amongst each other. Nonetheless, it is easier for respondents to respond, especially on sensitive topics
On the other hand, closed-ended questions contain suggestions that the respondent would otherwise not have had, hence influencing them. Frustration can also build up as the given opportunities may not represent what the respondent believed, hence being unable to make their voice heard.

23
Q

What are nonattitudes and middle positions?

A

When presented with two options of response, for example yes or no, some people may feel neutral towards the question or do not hold an opinion at all. This is why some researchers argue that a middle position should always be included.

24
Q

What is a standard-format question?

A

In the standard-format question, you do not offer a “don’t know” choice. A respondent would have to volunteer it.

25
Q

What is a quasi-filter question?

A

In a quasi-filter question, you offer respondents a “don’t know” alternative.

26
Q

What is a full-filter question?

A

A full-filter question is a special type of contingency question. You first ask respondents whether they have an opinion, then you ask for the opinion of those who stated that they have an opinion.

27
Q

What elements could influence the responses of participants?

A

Wording, question order and the context.

28
Q

How does the wording impact the response of a participant?

A

The words used have to be clear and explicit. They also have to be adjusted to the level of knowledge of the respondent. Otherwise, the respondent will not understand the question and will not be able to provide a reliable response.

29
Q

How does the question order impact the response of a participant?

A

The order in which you present questions might influence respondent answers. Respondents may not perceive each survey item as isolated and separate. They respond to survey questions based on the set of issues and their order of presentation. A previous question can influence later ones in two ways: through content (i.e., the substantive issue) and through the respondent’s response.

30
Q

What is a funnel question?

A

As a practical matter, for the same topic you want to use a funnel sequence of questions—that is, ask more general questions before specific ones (e.g., ask about health in general before asking about specific diseases).

31
Q

What is a matrix (or grid) question?

A

A Matrix question is a group of multiple-choice questions displayed in a grid of rows and columns. The rows present the questions to the respondents, and the columns offer a set of predefined answer choices that apply to each question in the row. Very often the answer choices are on a scale.

32
Q

How does the context impact the response of a participant?

A

Previous topics, past questions, or the question a respondent just heard can produce a context effect. The more ambiguous a question’s meaning, the stronger the context effects can be. Respondents will draw on the context as they interpret survey questions.

33
Q

What issues are there with the overall organisation of the questionnaire?

A

A questionnaire has opening, middle, and ending questions. After an introduction explaining the survey, it is best to make opening questions pleasant, interesting, and easy to answer. Organise questions into common topics. Mixing questions on different topics causes confusion. Orient respondents by placing questions on the same topic together and introduce the section with a short introductory statement (e.g., “Now I would like to ask you questions about housing”).

34
Q

Why is nonresponse an issue?

A

The failure to get a valid response from every sampled respondent weakens a survey. Nonresponse can be a major problem for survey research because if a high proportion of the sampled respondents do not respond, researchers may not be able to generalise results, especially if those who do not respond differ from those who do respond.

35
Q

What are the types of surveys?

A

Mail and self-administered questionnaires, web surveys, telephone interviews, face-to-face interviews and computer-assisted telephone interviewing.

36
Q

What are the advantages and disadvantages of mail and self-administered questionnaires?

A

Advantages: This type of survey is inexpensive, and is easy for a single researcher to conduct. With mail you can send questionnaires to a wide geographical area at a low cost. The respondent can complete the questionnaire when it is convenient and can check personal records if necessary. Mail questionnaires also offer anonymity and avoid interviewer bias.
Disadvantages: The biggest problem with mail questionnaires is a low response rate. Most questionnaires are returned within two weeks, but others trickle in up to two months later. You can raise response rates by sending nonrespondents several reminder letters, but this adds to the time and cost of data collection. Also, you have no control over the conditions under which a mail questionnaire is completed.

37
Q

What are the advantages and disadvantages of web surveys?

A

Advantages: They are fast and inexpensive. They allow flexible design and can use visual images, or even audio or video in some Internet versions.
Disadvantages: Sampling for this study can be inefficent because of unequal Internet access.

38
Q

What are the advantages and disadvantages of telephone interviews?

A

Advantages: The telephone interview is a popular survey method because almost the entire population can be reached by telephone. The process is straightforward: an interviewer calls a respondent (usually at home), asks questions, and records answers.
Disadvantages: Higher cost and limited interview length are among the disadvantages of telephone interviews. In addition, respondents without a telephone are impossible to reach. The use of an interviewer reduces anonymity and introduces potential interviewer bias. Open-ended questions are difficult to use, and questions requiring visual aids are impossible.

39
Q

What are the advantages and disadvantages of face-to-face interviews?

A

Advantages: Face-to-face interviews have the highest response rates and permit the longest questionnaires. Interviewers also can observe the surroundings and can use nonverbal communication and visual aids. Furthermore, the interviewer can use probes.
Disadvantages: High cost is the biggest disadvantage of face-to-face interviews. The training, travel, supervision, and personnel costs for interviews can be high. Interviewer bias is also greatest in face-to-face interviews. The appearance, tone of voice, question wording, and so forth of the interviewer may affect the respondent.

40
Q

What is a probe?

A

A probe is a neutral request to clarify an ambiguous answer, to complete an incomplete answer, or to obtain a relevant response. Interviewers recognise an irrelevant or inaccurate answer and use probes as needed. There are many types of probes. A three to five second pause is often effective. Non- verbal communication (e.g., tilt of head, raised eyebrows, or eye contact) also works well. The interviewer can repeat the question or repeat the reply and then pause. He or she can ask a neutral question, such as, “Any other reasons?”

41
Q

What is interviewer bias?

A

Interviewer bias argues that the respondent is influenced by the tone, behaviour and other aspects related to the researcher. Furthermore, perceived expectations from the interviewer can cause the respondent to offer different answers.

42
Q

What are the advantages and disadvantages of computer-assisted telephone interviews?

A

Advantages: With CATI, the interviewer sits in front of a computer and makes calls. Wearing a headset and microphone, the interviewer reads the questions from a computer screen that have been selected for the specific respondent who is called. The interviewer listens then enters the answer via the keyboard. This process speeds interviewing and introduces errors.
Disadvantages: Not all people have access to a telephone. Also, some might offer inaccurate answers, especially those from hidden populations.

43
Q

What types of interviews, in terms of structure, are there?

A

Structured, semi-structured and unstructured.

44
Q

What are structured interviews?

A

Structured interviews have preplanned questions, a rigid form and a high replicability.

45
Q

What are semi-structured interviews?

A

Semi-structured interviews have some preplanned questions, partial flexibility and partial replicability.

46
Q

What are unstructured interviews?

A

Unstructured interviews have no preplanned questions, they allow the use of probes, are very flexible and can hardly be replicated because of their diversity, complexity and uniqueness.

47
Q

What types of interview transcripts are there?

A

Full/pure verbatim, intelligent/smart verbatim and edited/non verbatim.

48
Q

What is a full/pure verbatim interview transcript?

A

It incorporates things like “hmm” and “uhm” which allow the researcher to interpret the behaviour of the participant.

49
Q

What is a intelligent/smart verbatim interview transcript?

A

It does not incorporate things like “hmm” and “uhm”. However, they maintain all other aspects of a participants’ response, even their grammar mistakes.

50
Q

What is a edited/non verbatim interview transcript?

A

It represents a fully edited form of the participants’ response and it may result into a loss of meaning.

51
Q

What ethical issues are related to privacy?

A

A major ethical issue in survey research is the invasion of privacy. You may intrude into a respondent’s privacy by asking about intimate actions and personal beliefs. Anxiety and discomfort should be eliminated by the researcher.

52
Q

What ethical issues are related to participation?

A

This issue involves voluntary participation by respondents. Respondents agree to answer questions and can refuse to participate at any time.

53
Q

What ethical issues are related to the exploitation of survey results?

A

Because of its popularity, some people have used surveys to mislead others. A pseudosurvey is when someone who has little or no real interest in learning information from a respondent uses the survey format to try to persuade someone to do something. Furthermore, sloppy reporting permits abuse, as the media distorts the findings of a true survey