Reliability

Question 1

what is test retest reliability

Answer 1

a method of assessing the reliability of a questionnaire or test by assessing the same person on 2 separate occasions
- shows to what extent the test produces the same answer

Question 2

what is inter observer reliability

Answer 2

• the extent to which there is agreement between 2 or more observers involved in observation of a behaviour
• measured by correlating the observation of 2 or more observers
• must be sufficient time between test and retest to ensure that participants cannot recall their answer but not so long ago that their behaviour has not changed

Question 3

how is reliability measured

Answer 3

• correlational analysis
  correlation coefficient should exceed +0.80 for reliability

Question 4

improving reliability in questionnaires

Answer 4

• use test retest method
• comparing two sets of data should provide a correlation that exceeds =0.8
• questionnaires that produce low test retest reliability may require some question to be rewritten as they are too complex or ambiguous so many be interpreted differently by the same person on different days
• replace open questions with closed fixed choice alternatives

Question 5

improving reliability in interviews

Answer 5

• use the same interviewer each time
• if not possible then all interviewers must be properly trained to not ask leading or ambiguous questions
• easier in structured interviews

Question 6

improving reliability in observations

Answer 6

• make sure behavioural categories have been properly operationalised and are measurable and self evident
• categories should not overlap and all possible behaviour should be covered on the checklist
• if categories are not well operations, overlapping or absent different observers will have to make their own judgement and may end up with inconsistent records

Question 7

improving reliability of experiments

Answer 7

• procedure has to be consistent every time
• standardised procedure