Questionnaire development Flashcards

1
Q

What is important to consider when writing your questions?

A
  • Be specific as you can with the wording
  • If a timescale is relevant, be specific
  • Avoid double negative questions
  • Avoid double barrelled questions (two issues)
  • Don’t induce a particular response
  • Be ethical
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What are the two types of responses?

A

Open and closed

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

What is an open question?

A
  • Allows for an unconstrained response
  • Gives rich detail about the topic
  • However more difficult to summarise
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What is a closed question?

A
  • Requires a choice from a predetermined option

- Easy to code and summarise options

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

Why would you want to create a questionnaire?

A
  • There is no existing measure

- Or an existing measure is flawed

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

Advantages of open questions

A

 Respondent is not forced to choose between options
 Respondent can give explanations for responses
 Respondent can give additional information they feel is relevant or important to their response

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

Disadvantages of closed questions

A

 Respondent can give additional information they feel is relevant or important to their response
 BUT: What if that information is not relevant to the survey?
 More time consuming for respondent
 Analysis is more complex and time consuming for you

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

Types of closed questions?

A
  • Categorical (male vs female)
  • Likert scale
  • Ranking (rank from favourite to least favourite)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What should be considered about categorical responses?

A
  • Need to be mutually exclusive (e.g. answers should not cross over)
  • If there are multiple answers, need to be clear on how many to select
  • Think about if you need a ‘other’ - how would you analyse this?
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

What is an item?

A

-asking the responder the extent to which they agree with a statement
 I like to have a lot of people around me
 Response: “strongly disagree” through to “strongly agree”

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

What is a question?

A

Asking a more explicit question

 Do you like to have a lot of people around you?  Response: “not at all” through to “very much”

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

What should be considered with likert scales?

A
  • Usually 5 responses but can be more or less
  • Can include a neutral but needs to be in the middle
  • Can start at 0 or 1 but needs to be consistent
  • Do no show the numbers
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

How can you avoid random responses?

A

-Acquiescence bias (always agreeing with items)
 Ensure the questionnaire is not too long
 Positive and negatively marked items

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

What should be considered with positive and negative scoring?

A
  • Only show participants the words
  • Have an equal amount of positive and negative
  • Randomise the order of the positive and negative responses
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What is a visual analogue scale?

A
  • Lines are typically 100mm
  • Provides scores 0-100
  • More fine measure, parametric and less prone to responder bias
  • Can be positive or negative
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

How should a questionnaire be ordered?

A
  • Put demographics at the beginning or end
  • Most important first
  • Don’t start with sensitive items
  • Go from general to particular
  • Factual to abstract
  • Closed to open
17
Q

Why does a questionnaire need to be valid?

A

To ensure that it’s measuring what you set out to measure

18
Q

Why does a questionnaire need to be reliable?

A

To provide a consistent measure

19
Q

Why would you use subscales?

A

If there is a large number of questions, you can group them into themes

20
Q

How can you measure validity and reliability?

A

Cronbach’s alpha