Test Bank Chapter 4 Conceptualization And Measurement

Chapter 7: Survey Research

Test Bank

MULTIPLE CHOICE

1. This is a feature of survey research that makes it popular to use (7-2)
2. Versatility
3. Omnibus approach
4. Focused
5. Simple

ANS [A]

LOC: What Is a Survey?

TIP: Attractive Features of Survey Research

[LO 1]

COG [Knowledge]

DIF [Easy]

1. An example of an omnibus survey is the (7-3)
2. GSS
3. Gallup poll
4. CSUS student survey
5. UCR

ANS [A]

LOC: What Is a Survey?

TIP: The Omnibus Survey

[LO 4]

COG [Knowledge]

DIF [Easy]

1. One of the key principles that should guide the design of any questionnaire is (7-4)
2. that is should have a very flexible focus
3. that it should be able address only one issue at a time
4. that it may build on existing instruments
5. that it should not be translated into other languages because different cultures will have different issues to face so surveys can only be written in an original language

ANS [C]

LOC: Questionnaire Development and Assessment

TIP: Build on Existing Instruments

[LO 4]

COG [Comprehension]

DIF [Medium]

1. In order to measure violent victimizations, the NCVS uses (7-3)
2. Vague questions to get the best possible range of answers
3. Screening questions to get the most relevant respondents to which questions will apply
4. Filtering questions to ask nonrelated items of respondents
5. All of the above

ANS [B]

LOC: Questionnaire Development and Assessment

TIP: Case Study: Measuring Violent Victimizations

[LO 2]

COG [Application]

DIF [Medium]

1. Writing survey questions (7-6)
2. Are always easy to make clear and unambiguous
3. Are best if they are written in the open-ended style
4. Can have a great effect on the way they are answered
5. Should allow for ambiguity so that a respondent can respond in many ways

ANS [C]

LOC: Writing Survey Questions: More Difficult Than You Think!

TIP: Writing Survey Questions: More Difficult Than You Think!

[LO 2]

COG [Analysis]

DIF [Medium]

1. A basic requirement for constructing clear questions is to (7-8)
2. Write clear and simply phrased questions
3. Make questions as wordy as possible to make sure respondents will be able to understand the question
4. Avoid confusing phrases and vagueness
5. Only A and C are correct

ANS [D]

LOC: Writing Survey Questions: More Difficult Than You Think!

TIP: Constructing Clear and Meaningful Questions

[LO 2]

COG [Application]

DIF [Hard]

1. Consider the question: “Do you disagree that juveniles should not be tried as adults if they commit murder?” Which of the following best describes the question? (7-9)
2. It is a double-negative question
3. It is a double-barreled question
4. It does not have a mutually exclusive response
5. None of the above

ANS [A]

LOC: Constructing Clear and Meaningful Questions

TIP: Avoid Negatives and Double Negatives

[LO 2]

COG [Analysis]

DIF [Medium]

1. When a question is asking more than one thing, it is known as a (7-9)
2. Double-negative question
3. Double-barreled question
4. Mutually exhaustive question
5. Mutually exclusive question

ANS [B]

LOC: Constructing Clear and Meaningful Questions

TIP: Avoid Double-Barreled Questions

[LO 2]

COG [Analysis]

DIF [Medium]

1. Some steps that may be taken in order to avoid seeming like they are disagreeable include (7-9)
2. The impartial presentation of both sides of the attitude scales of the question itself
3. Phrasing each response to make each seem socially approved
4. Asking about a variety of behaviors or attitudes that range from socially acceptable to socially unacceptable
5. All of the above

ANS [D]

LOC: Constructing Clear and Meaningful Questions

TIP: Avoid Making Either Disagreement or Agreement Disagreeable

[LO 2]

COG [Analysis]

DIF [Medium]

1. Creating clear and meaningful questions are important, but the choices you provide respondents in closed-ended questions are also important and include (7-10)
2. Making response choices mutually exclusive
3. Making response choices exhaustive
4. Both A and B are correct
5. None of the above

ANS [C]

LOC: Writing Survey Questions: More Difficult Than You Think!

TIP: Additional Guidelines for Closed-Ended Questions

[LO 2]

COG [Analysis]

DIF [Difficult]

1. Likert-type responses generally ask respondents to (7-11)
2. Indicate their neutrality about a statement
3. Indicate the extent to which they agree or disagree with a statement
4. Indicate that they choose a substantive answer when they are uninformed about a topic
5. None of the above

ANS [B]

LOC: Writing Survey Questions: More Difficult Than You Think!

TIP: Utilize Likert-Type Response Categories

[LO 2]

COG [Application]

DIF [Medium]

1. A floater is a person who (7-12)
2. Sees themselves as neutral in their attitudes toward a particular issue
3. Chooses a substantive answer even when they do not know anything about the topic
4. Seeks to ensure that a question has been filtered properly
5. Chooses to answer only contingent questions

ANS [A]

LOC: Writing Survey Questions: More Difficult Than You Think!

TIP: Minimize Fence-Sitting and Floating

[LO 2]

COG [Application]

DIF [Hard]

1. If the researcher is interested in utilization of police services by assault victims, it is helpful to establish victimization with (7-12)
2. A skip pattern
3. A contingent question
4. A filter question
5. None of the above

ANS [C]

LOC: Writing Survey Questions: More Difficult Than You Think!

TIP: Utilize Filter Questions

[LO 2]

COG [Synthesis]

DIF [Hard]

1. A skip pattern is (7-12)
2. A question that is asked only of a subset of survey respondents
3. The unique combination of questions created by filter questions and contingent questions
4. A question used to identify a subset of respondents who are then asked other questions
5. None of the above

ANS [B]

LOC: Writing Survey Questions: More Difficult Than You Think!

TIP: Utilize Filter Questions

[LO 2]

COG [Application]

DIF [Hard]

1. A researcher may choose to use several related questions in order to measure a variable, which is known as (7-13)
2. Idiosyncratic variable
3. An index or scale
4. A reliability measure
5. A demographic question

ANS [B]

LOC: Writing Survey Questions: More Difficult Than You Think!

TIP: Combining Questions Into an Index

[LO 2]

COG [Application]

DIF [Medium]

1. Demographic information may include (7-15)
2. Sex
3. Age
4. Income
5. All of the above

ANS [D]

LOC: Writing Survey Questions: More Difficult Than You Think!

TIP: Demographic Questions

[LO 2]

COG [Application]

DIF [Easy]

1. Certain questions may feel very intrusive to respondents, including questions about (7-15)
2. income
3. ethnicity
4. religion
5. all of the above

ANS [D]

LOC: Writing Survey Questions: More Difficult Than You Think!

TIP: Demographic Questions

[LO 2]

COG [Comprehension]

DIF [Easy]

1. Questionnaire organization should include (7-17)
2. A cover letter for a mailed questionnaire, including an introductory statement
3. Attention to question ordering in order to uncover attitudes about emotionally charged topics
4. Potential use of a split-ballot design in order to include more questions in randomly selected subsets of respondents
5. All of the above

ANS [D]

LOC: Organization Matters

TIP: Organization Matters

[LO 4]

COG [Synthesis]

DIF [Medium]

1. Surveys may be administered in several different ways, including (7-19)
2. Use of mail surveys
3. Use of electronic surveys
4. Use of group surveys
5. All of the above

ANS [D]

LOC: Survey Designs

TIP: Mailed (Self-Administered) Surveys

[LO 4]

COG [Knowledge]

DIF [Easy]

1. The most expensive type of survey is (7-20)
2. Self-administered
3. In-person
4. Phone
5. Electronic

ANS [B]

LOC: Survey Designs

TIP: Cost

[LO 4]

COG [Knowledge]

DIF [Easy]

1. The response rate for mailed (self-administered) surveys is generally around (7-20)
2. 20-25%
3. 35-40%
4. 70-80%
5. Over 90%

ANS [C]

LOC: Survey Designs

TIP: Mailed (Self-Administered) Surveys

[LO 4]

COG [Knowledge]

DIF [Medium]

1. The validity of a phone survey may be undermined when (7-21)
2. Not enough proper sampling units are reached
3. Not enough complete responses are received to make the survey generalizable
4. Not enough proper answers are given to a survey
5. Both A and B are correct

ANS [D]

LOC: Survey Designs

TIP: Surveys by Telephone

[LO 4]

COG [Analysis]

DIF [Hard]

1. Procedures may be standardized more effectively if phone interviewers are assisted by the use of (7-21)
2. Email
3. CATI
4. IVR
5. All of the above

ANS [B]

LOC: Surveys by Telephone

TIP: Maximizing Response to Phone Surveys

[LO 4]

COG [Application]

DIF [Medium]

1. Unique to the in-person interview compared to other survey designs is (&-22)
2. Use of the telephone to help with answering demographic questions
3. The face-to-face social interaction between interviewer and respondent
4. The inexpensive component of face-to-face interviewing
5. Use of computer assisted self-interviewing in addition to the in-person component

ANS [B]

LOC: Survey Designs

TIP: In-Person Interviews

[LO 4]

COG [Analysis]

DIF [Medium]

1. An advantage of in-person interviewing is (7-22)
2. That it is time-consuming
3. That response rates are lower than for survey research
4. That the physical and social circumstances of the interview can be monitored
5. All of the above

ANS [C]

LOC: Survey Designs

TIP: In-Person Interviews

[LO 4]

COG [Comprehension]

DIF [Medium]

1. The most reliable way to administer questionnaires when they probe sensitive or potentially stigmatizing information (offending or victimization information) is by using (7-22)
2. In-person interviews
3. Audio-CASI
4. CAPI
5. Electronic surveys

ANS [B]

LOC: Survey Designs

TIP: In-Person Interviews

[LO 4]

COG [Application]

DIF [Hard]

1. Combining survey designs allow the strength of one survey design to compensate for the weaknesses of another is known as (7-24)
2. Combination of survey methods
3. The use of mixed-mode surveys
4. Strength-weakness methods
5. None of the above

ANS [B]

LOC: Survey Designs

TIP: Mixed Mode Surveys

[LO 4]

COG [Synthesis]

DIF [Hard]

1. The best survey method is (7-26)
2. The in-person survey method
3. The phone survey method
4. The electronic survey method
5. Ultimately determine determined by the study’s unique features and goals rather than by any absolute standard of what the best survey is

ANS [D]

LOC: Survey Designs

TIP: A Comparison of Survey Designs

[LO 4]

COG [Evaluation]

DIF Hard]

1. Procedures to prevent harmful effects for the respondent should (7-26)
2. Be delineated, including how the researcher will keep interviews confidential and anonymous
3. Put protections in place after a survey has started whenever sensitive subject matter is discussed
4. Ensure that only one interviewer at a time speak with each interviewee
5. There are no procedures to protect respondents

ANS [B]

LOC: Ethical Issues in Survey Research

TIP: Protection of Respondents

[LO 5]

COG [Comprehension]

DIF [Medium]

1. When no identifying information can be obtained about a respondent, the responses are (7-28)
2. Confidential
3. Anonymous
4. Both confidential and anonymous
5. Neither confidential nor anonymous

ANS [B]

LOC: Ethical Issues in Survey Research

TIP: Protection of Respondents

[LO 5]

COG [Knowledge]

DIF [Easy]

TRUE/FALSE

1. Survey research involves the collection of information from a sample of individuals through their responses to questions. (7-2)
2. True
3. False

ANS [A]

LOC: Survey Research in Action: Measuring Victimization

TIP: What Is a Survey?

[LO 4]

COG [Knowledge]

DIF [Easy]

1. Versatility is an attractive feature of survey research. (7-2)
2. True
3. False

ANS [A]

LOC: Attractive Features of Survey Research

TIP: Versatility

[LO 4]

COG [Knowledge]

DIF [Easy]

1. While surveys have many popular features, unfortunately they are not generalizable. (7-2)
2. True
3. False

ANS [B]

LOC: Attractive Features of Survey Research

TIP: Efficiency

[LO 4]

COG [Knowledge]

DIF [Easy]

1. An omnibus survey covers a range of topics of interest. (7-3)
2. True
3. False

ANS [A]

LOC: What Is a Survey?

TIP: The Omnibus Survey

[LO 4]

COG [Knowledge]

DIF [Easy]

1. A Questionnaire is the survey instrument containing that questions for a self-administered survey. (7-3)
2. True
3. False

ANS [A]

LOC: What Is a Survey?

TIP: Questionnaire Development and Assessment

[LO 4]

COG [Comprehension]

DIF [Medium]

1. In the 21^st century, survey plans in the U.S. or many other countries are considered complete once the issue of translation into another language has been considered. (7-4)
2. True
3. False

ANS [B]

LOC: Questionnaire Development and Assessment

TIP: Consider Translation

[LO 4]

COG [Comprehension]

DIF [Hard]

1. Questions in the NCVS assess whether the respondent has experienced violent victimization within the past 6 months. (7-4)
2. True
3. False

ANS [A]

LOC: Questionnaire Development and Assessment

TIP: Case Study: Measuring Violent Victimization

[LO 1]

COG [Application]

DIF [Medium]

1. The time frame around which a question is being asked is called the reverence period. ( 7-9)
2. True
3. False

ANS [B]

LOC: Constructing Clear and Meaningful Questions

TIP: Avoid Confusing Phrasing and Vagueness

[LO 4]

COG [Comprehension]

DIF [Medium]

1. Survey questions to which the respondent replies in his/her own words, either by writing or talking, are closed-ended questions. (7-7)
2. True
3. False

ANS [B]

LOC: Questionnaire Development and Assessment

TIP: Writing Survey Questions: More Difficult Than You Think!

[LO 4]

COG [Comprehension]

DIF [Medium]

1. Fixed-choice questions are the same as closed-ended questions. (7-7)
2. True
3. False

ANS [A]

LOC: Questionnaire Development and Assessment

TIP: Writing Survey Questions: More Difficult Than You Think!

[LO 4]

COG [Knowledge]

DIF [Medium]

1. Clearly and simply phrased questions are most likely to have the same meaning for different respondents. (7-8)
2. True
3. False

ANS [A]

LOC: Writing Survey Questions: More Difficult Than You Think!

TIP: Avoid Confusing Phrases and Vagueness

[LO 4]

COG [Application]

DIF [Easy]

1. A question or statement that contains two negatives, known as a double- negative, can be very difficult to answer. (7-9)
2. True
3. False

ANS [A]

LOC: Writing Survey Questions: More Difficult Than You Think!

TIP: Avoid Double-Barreled Questions

[LO 4]

COG [Knowledge]

DIF [Easy]

1. “The county should stop spending so much money on prisons and should spend it on schools” is an example of a double-barreled question (7-9)
2. True
3. False

ANS [A]

LOC: Writing Survey Questions: More Difficult Than You Think!

TIP: Avoid Double-Barreled Questions

[LO 4]

COG [Comprehension]

DIF [Easy]

1. People often tend to agree with a statement just to avoid seeming disagreeable. (7-10)
2. True
3. False

ANS [A]

LOC: Writing Survey Questions: More Difficult Than You Think!

TIP: Avoid Making Either Disagreement or Agreement Disagreeable

[LO 4]

COG [Application]

DIF [Medium]

1. There is no rule regarding making response choices for closed-ended questions mutually exclusive. (7-10)
2. True
3. False

ANS [B]

LOC: Writing Survey Questions: More Difficult Than You Think!

TIP: Additional Guidelines for Closed-Ended Questions

[LO 4]

COG [Knowledge]

DIF [Easy]

1. All responses to questions with fixed-response categories must provide an answer option that fits for each respondent. (7-11)
2. True
3. False

ANS [A]

LOC: Writing Survey Questions: More Difficult Than You Think!

TIP: Additional Guidelines for Closed-Ended Questions

[LO 4]

COG [Knowledge]

DIF [Easy]

1. Fence-sitters are people who see themselves as neutral in their attitudes toward a particular issue. (7-12)
2. True
3. False

ANS [A]

LOC: Writing Survey Questions: More Difficult Than You Think!

TIP: Minimize Fence-Sitting and Floating

[LO 4]

COG [Application]

DIF [Medium]

1. Floaters are people who see themselves as neutral in their attitudes toward a particular issue. (7-12)
2. True
3. False

ANS [B]

LOC: Writing Survey Questions: More Difficult Than You Think!

TIP: Minimize Fence-Sitting and Floating

[LO 4]

COG [Application]

DIF [Medium]

1. A skip pattern is a unique combination of questions created in a survey by filter questions and contingent questions. (7-12)
2. True
3. False

ANS [A]

LOC: Additional Guidelines for Closed-Ended Questions

TIP: Utilize Filter Questions

[LO 4]

COG [Application]

DIF [Medium]

1. Reliability measures help decide whether responses actually measure what the researcher thinks it measures. (7-14)
2. True
3. False

ANS [B]

LOC: Additional Guidelines for Closed-Ended Questions

TIP: Combining Questions Into an Index

[LO 4]

COG [Comprehension]

DIF [Medium]

ESSAY

1. What is a survey? What are the features that make survey research attractive to researchers? (7-2)

Regardless of its scope, survey research owes its continuing popularity to three features: versatility, efficiency, and generalizability.

Versatility The first and foremost reason for the popularity of survey methods is their versatility. Researchers can ask respondents questions about almost any topic you can imagine. Although a survey is not the ideal method for testing all hypotheses or learning about every social process, a well-designed survey can enhance our understanding of just about any social issue. In fact, there is hardly any topic of interest to social scientists that has not been studied at some time with survey methods.

Computer technology has made surveys even more versatile. Computers can be programmed so that different types of respondents are asked different questions. Short videos or pictures can be presented to respondents on a computer screen. An interviewer may give respondents a laptop on which to record their answers to sensitive personal questions, such as about illegal activities, so that not even the interviewer will know what they said (Tourangeau, 2004).

Efficiency Surveys also are popular because data can be collected from many people at relatively low cost and, depending on the survey design, relatively quickly. Surveys are efficient research methods because many variables can be measured without substantially increasing the time or cost of data collection. Mailed questionnaires can include up to 10 pages of questions before most respondents lose interest (and before more postage must be added). The maximum time limit for phone surveys seems to be about 45 minutes. In-person interviews can last much longer, more than an hour.

Generalizability Survey methods lend themselves to probability sampling from large populations. Thus, survey research is very appealing when sample generalizability is a central research goal. In fact, survey research is often the only means available for developing a representative picture of the attitudes and characteristics of a large population.

Surveys also are the research method of choice when cross-population generalizability is a primary concern (see Chapter 5). They allow a range of social contexts and subgroups to be sampled, and the consistency of relationships can be examined across the various subgroups.

LOC: Survey Research in Action: Measuring Victimization

TIP: What Is a Survey?

[LO 4]

COG [Comprehension]

DIF [Medium]

1. What is an omnibus survey? How is an omnibus survey different from a survey directed at a specific research question? (7-3)

One of the most successful omnibus surveys is the General Social Survey (GSS) of the National Opinion Research Center at the University of Chicago. Today, the GSS is administered every two years as a 90-minute interview to a probability sample of almost 3,000 Americans. It includes more than 500 questions about background characteristics and opinions, with an emphasis on social stratification, race relations, family issues, law and social control, and morale. Although the NCVS and the NISVS are not exactly omnibus surveys (they were both developed to obtain detailed information on a number of phenomena related to victimization), they do cover related information, including injuries and medical care received for victimization, the cost of victimization (including costs incurred for medical care and property lost), and whether the victimization was reported to police or other victim service agencies.

LOC: What Is a Survey?

TIP: The Omnibus Survey

[LO 4]

COG [Comprehension]

DIF [Medium]

1. What are some of the differences between everyday conversations and standardized surveys? How does ‘asking clear and meaningful questions’ fit in?

• The same survey questions must be used with each person, not tailored to the specifics of a given conversation.
• Survey questions must be understood in the same way by people who differ in many ways.
• You will not be able to rephrase a survey question if someone does not understand it because that would result in asking the person a different question from the one you asked the others in your sample.
• Survey respondents do not know you and so cannot be expected to share the nuances of expression that you and those close to you use to communicate.

These features make a survey very different from natural conversation and make question writing a challenging and important task for survey researchers.

Questions must be very clear and specific about what is being asked of respondents. Note the differences in specificity between the rape screening questions used by the NISVS and the NCVS displayed in Exhibits 7.1 and 7.2. It is logical that the multiple behaviorally specific questions from the NISVS will be associated with greater disclosure by survey respondents compared to the one question about sexual intercourse posed by the NCVS. Research has shown that questions that are written with more behavior-specific language, such as those used by the NISVS, result in much better recall by respondents of these types of victimizations compared to the questions used by the NCVS (Bachman, 2012; Fisher, 2009).

LOC: Writing Survey Questions: More Difficult Than You Think!

TIP: Constructing Clear and Meaningful Questions

[LO 4]

COG [4]

DIF [Hard]

1. The authors of your text argue that virtually all questions about behavior will be more reliable if they refer to specific times and events. What do they mean by this?

In general, research shows that the longer the reference period, the greater the underreporting of a given behavior (Cantor, 1984, 1985; Kobelarcik, Alexander, Singh, & Shapiro, 1983). As a general rule, when respondents are being asked about mundane or day-to-day activities, reference periods should be no longer than “in the past month.” However, when rare events are being measured, such as experiences with victimizations, “in the last six months” (as utilized by the NCVS) or “in the past 12 months” (as used by the NISVS) are both more appropriate. By using longer reference periods such as these, we will more likely capture these rarer events.

LOC: Constructing Clear and Meaningful Questions

TIP: Avoid Confusing Phrases and Vagueness

[LO 4]

COG [Application]

DIF [Medium]

1. What is a double-barreled question? Give an example and explain why they can be a problem when asking questions. What does it mean to ‘avoid making either disagreement or agreement disagreeable? Example? (7-9)

Have you ever used cocaine or know anyone who has ever used cocaine?

____ Yes ____ No

Double-barreled question -- A single survey question that actually asks two questions but allows only one answer.

LOC: Constructing Clear and Meaningful Questions

TIP: Avoid Double-Barreled Questions

[LO 4]

COG [Comprehension]

DIF [Medium]

1. What kinds of interviewing options are there with regard to surveys? What is unique to in-person interviews compared to other survey designs? (7-22)

What is unique to the in-person interview, compared to the other survey designs, is the face-to-face social interaction between interviewer and respondent. If financial resources are available for hiring interviewers to go out and personally conduct the surveys with respondents, in-person interviewing is often the best survey design.

LOC: Survey Designs

TIP: In-Person Interviews

[LO 4]

COG [Knowledge]

DIF [Medium]

1. There are two important guidelines for when a researcher wishes to ask closed-ended questions. What are they? Why are they important?

Make Response Choices Mutually Exclusive

When you want respondents to make only one choice, the fixed-response categories must not overlap. For example, if you were interested in the ways foot patrol officers spent their time while working, you might ask the following question:

On average, how much time do you spend on the job each week taking care of traffic violations?

• Less than 1 hour
• 1–3 hours
• 3–6 hours
• 6–10 hours
• 10 hours or more

The choices provided for respondents in this question are not mutually exclusive responses because they overlap. Which choice would an officer select if he or she spent three hours a week on traffic violations? Choices that are mutually exclusive would look like this:

• 1 hour or less
• 2–3 hours
• 4–6 hours
• 7–10 hours
• 11 hours or more

Make the Response Categories Exhaustive

In addition to mutual exclusivity, fixed-response categories must also allow all respondents to select an option. Consider the same research question about foot patrol officers. Suppose we asked a question such as this:

In what activity do you spend the most time in an average week on the job?

• traffic violations
• disturbance-related issues
• felony arrests
• misdemeanor arrests

Regardless of how exhaustive we think the response categories are, there must always be an option for respondents who require another choice. Exhaustive response categories can easily be created if respondents are provided with a choice labeled

• Other, please specify: ___________

Note, however, that “Other” should be used only after you have included all options that you believe to be relevant. Otherwise, a large percentage of respondents will select the “Other” category and you will have to spend time coding their responses.

Mutually exclusive responses -- Response choices on a survey that do not overlap.

Exhaustive responses -- A variable’s attributes or values in which every case can be classified as having one attribute.

LOC: Writing Survey Questions: More Difficult Than You Think!

TIP: Additional Guidelines for Closed-Ended Questions

[LO 4]

COG [4]

DIF [Hard]

1. What are Likert-type responses? How are they useful? (7-11)

I think “three strikes” laws that increase penalties for individuals convicted of three or more felonies will help to decrease the crime rate.

Strongly Agree Agree Disagree Strongly Disagree

1 2 3 4

Likert-type responses -- Survey responses in which respondents indicate the extent to which they agree or disagree with statements.

LOC: Additional Guidelines for Closed-Ended Questions

TIP: Using Likert-Type Response Categories

[LO 4]

COG [Application]

DIF [Hard]

1. What is meant by fence-sitting and floating? Give an example of each. (7-12)

Fence-sitters are people who see themselves as neutral in their attitudes toward a particular issue. If you are truly interested in those who do not have strong feelings on an issue, one alternative is to provide a neutral or undecided response option. The disadvantage of these options is that they may encourage some respondents to take the easy way out rather than really thinking about their feelings. They may also provide an out for respondents who do not want to reveal how they truly feel about an issue. On the other hand, not providing respondents who really have no opinion on an issue with an option such as “undecided” can be very frustrating for them and may encourage them to leave the item blank. Whatever you decide, it is generally a good idea to provide respondents with instructions that ask them to “select the choice in each item that most closely reflects your opinion.” This should help make all respondents feel more comfortable about their answers, particularly those who only slightly feel one way or the other.

Floaters are respondents who choose a substantive answer even when they do not know anything about a particular question. For example, research has shown that one third of the public will provide an opinion on a proposed law they know nothing about if they are not provided with a “don’t know” response option (Schuman & Presser, 1981). Of course, providing a “don’t know” option has the same disadvantage as providing a neutral response option: Its inclusion leads some people who have an opinion to take the easy way out.

Fence-sitters -- Survey respondents who see themselves as being neutral on an issue and choose a middle (neutral) response that is offered.

Floaters -- Survey respondents who provide an opinion on a topic in response to a closed-ended question that does not include a “don’t know” option, but will choose “don’t know” if it is available.

LOC: Additional Guidelines for Closed-Ended Questions

TIP: Minimize Fence-Sitting and Floating

[LO 4]

COG [Application]

DIF [Hard]

1. Sometimes we want to ask questions only of respondents to whom they are relevant. Define how a researcher would do that in a questionnaire and give an example as to how it works.

Filter question: A survey question used to identify a subset of respondents who then are asked other questions.

Skip patterns: The unique combination of questions created in a survey by filter questions and contingent questions.

Contingent question: Questions that are asked of only a subset of survey respondents.

Exhibit 7.3 Filter Questions and Skip Patterns

LOC: Additional Guidelines for Closed-Ended Questions

TIP: Utilize Filter Questions

[LO 4]

COG [Application]

DIF [Hard]

1. What is an index? When might it be used? (7-13)

As noted above, if just one question is used to measure a variable, the researcher may not realize respondents had trouble with a particular word or phrase in the question. Although writing carefully worded questions will help reduce idiosyncratic variation, when measuring concepts, the best option is to devise an index of multiple rather than single questions.

When several questions are used to measure one concept, the responses may be combined by taking the sum or average of the responses. A composite measure based on this type of sum or average is called an index or scale. The idea is that idiosyncratic variation in response to single questions will average out, so the main influence on the combined measure will be the concept focused on by the questions. In addition, the index can be considered a more complete measure of the concept than can any one of the component questions.

Idiosyncratic variation: Variation in responses to questions that is caused by individuals’ reactions to particular words or ideas in the question instead of by variation in the concept that the question is intended to measure.

Index: A composite measure based on summing, averaging, or otherwise combining the responses to multiple questions that are intended to measure the same variable.

Scale: A composite measure of one concept created from a series of two or more questions.

Creating an index, however, is not just a matter of writing a few questions that seem to focus on one concept. Questions that seem to you to measure a common concept might seem to respondents to concern several different issues. The only way to know that a given set of questions does effectively form an index is to administer the questions in a pretest to people similar to the sample you plan to study. If a common concept is being measured, people’s responses to the different questions should display some consistency. Special statistics called reliability measures help researchers decide whether responses are consistent. Most respondent attitudes are complex and consist of many elements.

Reliability measures: Special statistics that help researchers decide whether responses are consistent.

Be aware of response sets when constructing an index measuring attitudes. For example, some people tend to agree with almost everything asked of them, whereas others tend to disagree. Still others are prone to answer neutrally to everything if given the option. To decrease the likelihood of this happening, it is a good idea to make some statements both favorable and unfavorable to a particular attitude to vary the response choices and still reach an understanding of an individual’s opinion. In this way, respondents are forced to be more careful in their responses to individual items. Exhibit 7.4 displays a hypothetical set of questions designed to solicit respondents’ attitudes toward police in their community.

When scoring an index or scale made up of both favorable and unfavorable statements, you must remember to reverse code the unfavorable items. For example, marking “strongly agree” on the first item in Exhibit 7.4 should not be scored the same as a “strongly agree” response to the second item.

Exhibit 7.4 Items in an “Attitude Toward Police” Index

LOC: Additional Guidelines for Closed-Ended Questions

TIP: Combining Questions Into AnIndex

[LO 4]

COG [Application]

DIF [Hard]

1. What are reliability measures? How are they used? (7-14)

When scoring an index or scale made up of both favorable and unfavorable statements, you must remember to reverse code the unfavorable items. For example, marking “strongly agree” on the first item in Exhibit 7.4 should not be scored the same as a “strongly agree” response to the second item.

LOC: Writing Survey Questions: More Difficult Than You Think!

TIP: Combining Questions Into an Index

[LO 2]

COG [Application]

DIF [Hard]

1. Give an example of demographic questions and explain why it is often very important to use them in research. (7-15)

LOC: Writing Survey Questions: More Difficult Than You Think!

TIP: Demographic Questions

[LO 3]

COG [Application]

DIF [Easy]

1. What are the five basic survey designs? Give an example of each. (7-19)

A mailed (self-administered) survey is conducted by mailing a questionnaire to respondents, who then administer the survey themselves. The principal drawback in using this method of survey administration is the difficulty maximizing the response rate—we have to rely on people to voluntarily return the surveys! The final response rate is unlikely to be much above 80% and almost surely will be below 70% unless procedures to maximize the response rate are precisely followed. A response rate below 60% is a disaster, and even a 70% response rate is not much more than minimally acceptable. It is hard to justify the representativeness of the sample if more than a third of those surveyed fail to respond.

A group-administered survey is completed by individual respondents assembled in a group. The response rate is not usually a concern in surveys that are distributed and collected in a group setting because most group members will participate. The difficulty with this method is that assembling a group is seldom feasible because it requires a captive audience. With the exception of students, employees, members of the armed forces, and some institutionalized populations, most populations cannot be sampled in such a setting.

In a phone survey, interviewers question respondents over the phone and then record their answers. Phone interviewing has become a very popular method of conducting surveys in the United States because almost all families have phones. But two matters may undermine the validity of a phone survey: not reaching the proper sampling units and not getting enough complete responses to make the results generalizable.

What is unique to the in-person interview, compared to the other survey designs, is the face-to-face social interaction between interviewer and respondent. If financial resources are available for hiring interviewers to go out and personally conduct the surveys with respondents, in-person interviewing is often the best survey design.

Electronic surveys have become increasingly useful for two reasons: growth in the fraction of the population using the Internet and technological advances (often using the Web or e-mail) that make electronic survey design, often done using the Web or email, relatively easy.

LOC: Organization Matters

TIP: Survey Designs

[LO 4]

COG [Comprehension]

DIF [Medium]

1. What are the ethical issues in survey research? (7-26)

Protection of Respondents: If the survey could possibly have any harmful effects for the respondents, these should be disclosed fully in the cover letter or introductory statement (recall the discussion of informed consent in Chapter 3). The procedures used to reduce such effects should also be delineated, including how the researcher will keep interviews confidential and anonymous. In addition, surveys such as the NISVS and NCVS that attempt to measure sensitive subject matter such as rape and intimate-perpetrated assault should also have other protections in place. When asking about victimizations, particularly those that are perpetrated by known offenders and family members, the World Health Organization (WHO) has been at the forefront of establishing policies to protect respondents. As WHO notes, “The primary ethical concern related to researching violence against women (VAW) is the potential for inflicting harm to respondents through their participation in the study” (Ellsberg & Heise, 2005, p. 38). Because many perpetrators of IPV use control as a form of abuse, a respondent may suffer physical harm if an abuser finds out that he or she disclosed information about their relationship to an interviewer. Guidelines to prevent this from happening include interviewing only one person in the household (Ellsberg & Heise, 2005). In addition, a graduated informed consent process is also recommended. For example, when first contacting a potential respondent, the initial person who answered the telephone should be provided only general information about the survey topic (e.g., on health-related issues). Only after a respondent is selected from a household should they be told about the specific topics that would be covered (e.g., violent victimizations). Interviewers should also remind respondents that they can stop the interview at any time, and safety plans should be established between the interviewer and the respondents.

Minimizing respondents’ distress by reliving victimization events and providing them with information on services and resources that can help their situation are also necessary. For example, the NISVS provided telephone numbers for the National Domestic Violence Hotline and the Rape, Abuse, and Incest National Network at the end of interviews. The College Risk Behavior Survey discussed earlier in this chapter also gave respondents information about a number of avenues for help seeking, including the phone numbers to the University of Delaware Center for Counseling and Student Development, the Delaware Council on Gambling Problems, and the Delaware 24-Hour Rape Crisis Hotline. As you can see in Exhibit 7.9, the last screen of the survey provided this information to respondents.

Respondent protection is even more complicated when asking about victimizations against minor children, as the NCVS does (e.g., it interviews individuals aged 12 or older). Currently, researchers do not fall under the purview of mandatory reporters, according to most state statutes, and the WHO claims there is no consensus internationally about how to handle cases of child abuse (Bachman, 2012). This is true for cases of elder abuse that are reported by respondents as well. Regardless of statutes not explicitly listing researchers as mandatory reporters, however, interviewers should certainly be required to develop protocols to act in the best interests of a child or an elder when cases of these forms of abuse are revealed.

Confidentiality: Do any of the questions have the potential to embarrass respondents or otherwise subject them to adverse consequences such as legal sanctions? If the answer to this question is no—and it often is in surveys about general social issues—other ethical problems are unlikely. But if the questionnaire includes questions about attitudes or behaviors that are socially stigmatized or generally considered to be private or questions about actions that are illegal, the researcher must proceed carefully and ensure that respondents’ rights are protected.

The first step to take with potentially troublesome questions is to consider modifying them or omitting them entirely. If sensitive questions fall into this category, they probably should be omitted. There is no point in asking, “Have you ever been convicted of a felony?” if the answers are unlikely to be used in the analysis of survey results.

Many surveys—particularly surveys interested in delinquent or criminal offending behavior—do include some essential questions that might prove damaging to the subjects if their answers were disclosed. To prevent any possibility of harm to subjects due to disclosure of such information, it is critical to preserve subject confidentiality. No one other than research personnel should have access to information that could be used to link respondents to their responses, and even that access should be limited to what is necessary for specific research purposes. Only numbers should be used to identify respondents on their questionnaires, and the researcher should keep the names that correspond to these numbers in a separate, safe, and private location, unavailable to others who might otherwise come across them. Follow-up mailings or contact attempts that require linking the ID numbers with names and addresses should be carried out by trustworthy assistants under close supervision.

Only if no identifying information about respondents is obtained can surveys provide true anonymity to respondents. In this way, no identifying information is ever recorded to link respondents with their responses. However, the main problem with anonymous surveys is that they preclude follow-up attempts to encourage participation by initial nonrespondents, and they prevent panel designs, which measure change through repeated surveys of the same individuals. In-person surveys rarely can be anonymous because an interviewer must in almost all cases know the name and address of the interviewee. However, phone surveys that are meant only to sample opinion at one point in time, as in political polls, can safely be completely anonymous. When no follow-up is desired, group-administered surveys also can be anonymous. To provide anonymity in a mail survey, the researcher should omit identifying codes from the questionnaire but could include a self-addressed, stamped postcard so the respondent can notify the researcher that the questionnaire has been returned, without being linked to the questionnaire itself (Mangione, 1995).

LOC: Survey Designs

TIP: Ethical Issues in Survey Research

[LO 5]

COG [Comprehension]

DIF [Medium]