Reliability Flashcards
1
Q
What is Reliability?
A
- A measure of consistency.
2
Q
What are the two ways of measuring Reliability?
A
- Test-retest
- Inter-observe reliability
3
Q
What is the Test-retest method?
A
- Administering the same test/questionnaire to the same people on different occasions (results should be similar)
- Most commonly used with questionnaires/psychological tests but can be with interviews
4
Q
What is inter-observer Reliability?
A
- Observations = subjective/biased. Should be conducted in a group of two+, Inter-observer reliability may be established through a pilot study with a comparison at the end, the data collected should be correlated to assess reliability. In content analysis call inter-rater reliability and in interviews inter-interviewer reliability.
5
Q
How is Reliability measured?
A
- Using a correlational analysis, in test-retest and inter-observer reliability, the two sets of scores are correlated. The correlation coefficient should exceed +.80 for reliability
6
Q
What is the Correlation ‘test’?
A
- Correlated through a statistical test e.g Spearman’s rho, once test has been performed on two sets of data, a correlation coefficient will be calculated, must be 80+ for data to be reliable
7
Q
How can reliability be improved in Questionnaires?
A
- Should be measured using the test-retest method
- Avoid complex or ambiguous questions
- Replace open questions with closed, fixed choice alternatives
8
Q
How can reliability be improved in Interviews?
A
- Use same interviewer each time,
- all interviewers must be properly trained to not ask leading/ambiguous endings
- more easily avoided in structured interviews
9
Q
How can reliability be improved in Observations?
A
- Behavioural categories are properly operationalised (measurable and self-evident) and should not overlap
10
Q
How can reliability be improved in Observations?
A
- Procedures must be consistent (standardised procedures)