Reliability Flashcards

1
Q

Reliability

A

Refers to how consistent a measuring device is

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

What are the 4 ways to assess reliability

A
  • Test-retest reliability
  • Inter-observer reliability
  • Inter-rater reliability
  • Inter-interviewer reliability
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Test retest reliability

A

Assess reliability of a questionnaire by assessing the same person on two separate occasions

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

Inter observer reliability

A

Extent to which there is a agreement between two or more observers involved in observations of behaviour

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

Inter rater reliability

A

A research technique that indirectly studies behaviour by examining communications that people produce

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

Inter interviewer reliability

A

Measured during interviews, where he interview is conducted by two or more different people and then will compare conclusions

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

How to measure reliability

A

Through correlation coefficient

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

Correlations and reliability

A

If a study is reliable it will produce a correlation coefficient of 0.8 (strong relationship)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Ways to improve reliability in questionnaires

A
  • Test retest
  • If low retest reliability, sme items need to be rewritten or deselected
  • Closed, fixed choice questions
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Ways to improve reliability in interviews

A
  • Same interviewer(s)
  • Train all interviewers
  • Provide the interviewer with a list of questions to ask
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

Ways to improve reliability in observations

A
  • Behavioural categories
  • Ensure categories don’t overlap
  • If reliability is low ten observers may require further training
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

Ways to improve reliability in experiments

A
  • Procedure is the focus
  • Standardised instructions
How well did you know this?
1
Not at all
2
3
4
5
Perfectly