Chapter 6: Surveys and Observations

Question 1

Open-ended

Answer 1

Allows respondents to answer in any way they see fit. Can be difficult to code and categorize these responses.

Question 2

Forced-choice

Answer 2

Pick the best of two or more options.

Question 3

Likert scale

Answer 3

Rate the degree of agreement with each statement. Researchers place “anchors” on the numbers (strongly agree/disagree).

Question 4

Semantic differential format

Answer 4

Rate a target object using a numeric scale that is anchored with adjectives.

Question 5

Double-barreled questions

Answer 5

Incorporates two questions into one, which are difficult for participants to accurately answer.

Question 6

Leading questions

Answer 6

Leading the participant to a particular response through the question wording.

Question 7

Negatively worded question

Answer 7

A question in a survey or poll that contains negatively phrased statements, making its wording complicated or confusing and potentially weakening its construct validity.

Question 8

Question order

Answer 8

This matters within a questionnaire and the order that questionnaires are presented in.

Question 9

Response sets

Answer 9

A shortcut respondents may use to answer items in a long survey, rather than responding to the content of each item.

Question 10

Acquiescence or yea-saying

Answer 10

When people say “yes” or “strongly agree” without thinking carefully about each item.

Question 11

Nay-saying

Answer 11

When people say “no” or “disagree” with every item.

Question 12

Reverse-worded items

Answer 12

Items that are worded to mean the opposite of other items in the scale to spot participants using response sets to answer items.

Question 13

Fence sitting

Answer 13

Playing it safe by answering in the middle of the scale, especially when survey items are controversial.

Question 14

Socially desirable responding/Faking good

Answer 14

Giving answers on a survey (or other self-report measure) that make one look better than one really is.

Question 15

Faking bad

Answer 15

Giving answers on a survey (or other self-report measure) that make one look worse than one really is.

Question 16

Ways to avoid socially desirable responding

Answer 16

1. Make survey anonymous (may treat less seriously/accurately)
2. Include special survey items that ID socially desirable responders
3. Ask people’s friends to rate them
4. Computerized measures like the Implicit Association Test

Question 17

Ways to avoid fence-sitting

Answer 17

1. Take away the neutral option (not great for people who are truly ambivalent)
2. Use forced-choice questions

Question 18

Survey/Poll

Answer 18

A method of posing questions to people online, in personal interviews, or in written questionnaires.

Question 19

Observational research

Answer 19

When a researcher watches people or animals and systematically records how they behave or what they are doing.

Question 20

Observer bias

Answer 20

Observers record what they want to see or expect to see, rather than what is really happening. Participant behavior may not change but the interpretation of it by the researcher does.

Question 21

Observer effects

Answer 21

Due to subtle cues from the researcher, the participants confirm the observer’s expectations.

Question 22

Preventing observer bias and observer effects

Answer 22

Training, codebooks, multiple observers, or blind (i.e., masked) design.

Question 23

Masked/blind design

Answer 23

The observers are unaware of the purpose of the study and the conditions to which participants have been assigned.

Question 24

Reactivity

Answer 24

Participant reacts to being watched and behaves differently.

Question 25

How to handle reactivity

Answer 25

1. Blend in unobtrusive observations (e.g., one-way mirror).
2. Wait it out- let the participant get used to your presence.
3. Measure the behavior’s results - rather than directly observing the participants, measure something related to the behavior.

Question 26

Keeping observational research ethical

Answer 26

1. How people behave in public places is done with the expectation that others will see it. (no informed consent)
2. We don’t report the behavior of specific participants, but of the group as a whole.
3. More secretive observation or observation of private behaviors should be done with the permission of the participants (i.e., informed consent).
4. Video/audio taping must get special permission. Has to be highlighted!

Question 27

4 basic questions format (frequency claim)

Answer 27

1. Open-ended
2. Forced-choice
3. Likert scale
4. Semantic differential format

Question 28

Reasons to use behavioral observation over self-report

Answer 28

May be better than self-reports because of the limitations we just discussed (response sets, social desirability).
May be better than self-reports because it can provide more detailed and rich information.
Sometimes self-report may not be possible (how many times do you smile per day?).