Reliability

Question 1

What is reliability?

Answer 1

• Reliability is the measure of consistency. For example, if a measurement is made twice and produces the same result, it can be said to be reliable.

Question 2

What are ways to assess reliability?

Answer 2

• Test - retest
• Inter - observer reliability
• Measuring reliability

Question 3

What is Test - Retest?

Answer 3

• This involves administering the same test or questionnaires to the same person or people on multiple different occasions.
• If a test or questionnaire is relaible, the results obtained should be the same or similar
• There has to be sufficient time between the test and retest to ensure that the participants cant recall previous answers but not too long so opinions change
• If the correlation between two answers is significant, reliability is good

Question 4

What is inter - observer reliability?

Answer 4

• inter observer reliability helps to determine subjectivity, bias and unreliability in the data collection process
• This can involve a small - scale trial run ( a plilot study) of the observation to ensure that observers are applying behavioural categories in the same way
• Observers may need to watch and rewatch sequences of events and record their data independently to ensure that the observations are reliable
• This can be done for test - retest, interviews (inter - interviewer reliability) and content analysis ( inter - rater reliability)

Question 5

How do you measure reliability?

Answer 5

• Reliability can be measured using a correlational analysis
• in test - retest and inter - observer reliability the two tests can be correlated
• the correlation coefficient has to exceed +0.80 for reliability

Question 6

What are ways to improve reliability in questionnaires?

Answer 6

• Questionnaires should be measured by finfing a correlation between two test - retests and comparing them
• A questionnaire that produces low test - restest reliability may require some items to be deselected
• Complex or ambiguous answers can be due to difficult questions with bad wording
• A solution to imptove this can be using closed or fixed choice alternatives

Question 7

How do you improve reliability of interviews?

Answer 7

• To improve reliability, you can use the same interviewer each time
• If this is not possible, interviewers have to be properly trained and not leading or ambiguous
• This is easier in structured interviews

Question 8

How do you improve reliability in observations?

Answer 8

• Making sure that observations are properly operationalised, measurable and self evident
• For example, pushing is less open to interpretation than aggression
• if reliability is low, observers may need further training in behavioural categories

Question 9

How do you improve the reliability of experiments?

Answer 9

• To make sure results are consistent, researchers can use standardised procedures.