Survey Flashcards
Survey
Descriptive technique designed to gather info from many people, usually by administering a questionnaire. It is used to evaluate specific attitudes or behaviours.
Questionnaire
Asks people questions about themselves (attitudes, behaviours, etc.) usually using a paper and pencil format
Designing a questionnaire
- Clearly define the topic of study.
Demographic information
info concerning the characteristics of participants (e.g., age, gender, marital status, etc.) It is often used as predictor variables.
What are the different types of questions on a questionnaire?
- Open ended
2. Close ended
Open Ended
Allows the participant to provide a response in his/her own words. They may provide more complete info but are difficult to analyze
e.g., Comment on whether you believe a student should or should not arrive at class on time.
Close Ended
A fixed alternative- provides alternatives for the participant. There’s more control over responses and they are easier to analyze but the info is not as rich.
Options for closed-ended questions
- Ordered alternatives
- Alternatives that are not ordered
- Yes/No Questions
Ordered Alternatives
About how often were you late for class in the past 12 months?
Not at all
Once or twice
About once a month
Two or three times a month
About once a week
Two or three times a week
Four or more times a week
Alternatives that are not ordered
If a student is late for class, they should:
not enter the classroom
enter through the back doors only
enter through any door
Yes/No Questions
A student should always arrive on time.
Yes. No.
Rating scales
A variation of close ended questions that provides a graded response to a question.
Examples of a rating scale
Examples:
A student should arrive at classes on time. (1-7) 1, being always and 7 being never.
Examples:
A student should arrive at classes on time.
(1-7) 1, being always, 4, being sometimes and 7, being never.
or you can provide an anchor at each end, as well as in the middle
Linkert Scale
Used for measuring attitudes. It provides a series of statements for participants to indicate degree of agreement/disagreement.
1- strongly disagree 2- disagree 3- undecided 4- agree 5- strongly agree
Partially open ended questions
Provide an “other” category so the participant can specify an answer
Combination questions
Have a closed-ended portion and an open ended portion so the participant can comment on their choice.
1- strongly disagree
5- strongly agree
Comment why:
Also want to include a positively and negatively keyed item to avoid response set bias.
Response set bias
The subject consistently picks ‘agree’ or ‘disagree’ regardless of the question being asked
Positively keyed items
Agreement means a positive attitude toward the issue.
The premier is doing a good job a cutting the budget.
Negatively keyed items
Agreement means a negative attitude toward the issue.
The premier is not doing a good job cutting the budget.
Additional comments on question construction
- create precise questions that only elicit the info you are interested in
- keep the wording simple
- avoid double negatives
- avoid biased wording
- give precise time referents
- do not ask double questions (ask one question at a time)
Face-to-face interviews… Advantages and Disadvantages
Advantages - you can gauge the respondent’s state
- you can judge comprehension and clear up misunderstandings
- you can probe for additional info
- they have higher completion rates and more complete info
Disadvantages - expensive, which limits the number that can be administered
- the interviewer can bias the results
- the respondent may not be honest, particularly with sensitive issues
Telephone interviews.. Advantages and Disadvantages
Advantages - more cost effective than face-to-face interviews
Disadvantages - respondents may get lost in long questions (keep questions short)
- respondents may be suspicious
- you may anger respondents by “catching them at a bad time”
Mail questionnaires
Advantages - inexpensive and can be administered to large samples over large areas
- participants may respond more honestly
Disadvantages - they may not be returned
Non Response Bias
With a very low return rate you may have a biased sample- for mail questionnaire’s
