Chapter 8

Question 1

Internal consistency

Answer 1

The degree to which the individual questions of a construct are correlated
Variables should relate to one another but not too much

Question 2

Pilot and pretesting

Answer 2

Pilot study: a small-scale version of the intended main research study, 50-200 respondents who are representative of the main study’s defined target population
Pretesting: a descriptive research activity representing a small scale investigation of 10-30 subjects representative of the main study’s defined target population but focus on a specific subcomponent of the main study

Question 3

Structured questions - quantitative

Answer 3

Close-ended questions that require the respondent to choose from a predetermined set of responses or scale points
Reduces respondent effort
Easy to answer and code

Question 4

Unstructured questions - qualitative

Answer 4

Open-ended questions that enable respondents to reply in their own words
Responses are unaided and unlimited
Difficult to code
Questions require more thought
Work best in self-administered and in-person
Often skipped

Question 5

Screening questions

Answer 5

Used in most questionnaires, their purpose is to identify qualified prospective respondents and prevent unqualified respondents from being included in the study

Question 6

Skip questions

Answer 6

Used if the next question (or set of questions) should be responded to only by respondents who meet a previous condition

Question 7

Response order bias

Answer 7

Occurs when the order of the question, or of the closed-end responses to a particular question, influences the answer given

Question 8

Things a researcher should do after preparing a survey but before getting approval

Answer 8

Focus on whether each question is necessary, length is acceptable
Survey should meet research objectives
Scale format and instructions should work well
General to specific questions
Paper surveys should be physically inspected
Professional and visually appealing

Question 9

Sampling errors

Answer 9

The difference between the findings based on the sample and the true values for a population
Caused by the method of sampling used and the size of the sample
Can be reduced by increasing the sample size and using the appropriate methods

Question 10

Non sampling errors

Answer 10

Errors that occur not related to sampling
Four sources: respondent error, measurement/questionnaire design, incorrect problem definition, project administration
These errors create systematic variation (bias), are controllable, cannot be measured directly, can create other non-sampling errors

Question 11

Topic sensitivity

Answer 11

The degree to which a survey question leads the respondent to give a socially acceptable response