relibaility

Question 1

reliability

Answer 1

• measure of consistency
• includes psychological tests or observations which assess behaviour

Question 2

ways of assesing reliability

test retest reliability

Answer 2

• asses relaibility of a questionaire or psychological test by assesing same person on 2 seperate occassions
• shows to what extent the test produces the same answer
• eg consistent or relibale

Question 3

ways of assessing reliability

inter-observer reliabilty

Answer 3

• the extent to which theres agreement between 2 or more observers involved in observations of a behaviour
• this is measured by correlating the observations of 2 or more observers
• gerneral rule is that if (total number of agreements)/(total number of observations) is more than +.80=the data has high IOR

Question 4

interobserver
observations

Answer 4

Observations should be carried out in teams or at least two and they should compare their observations.

Before observing, they should agree on behavioural categories.

Observers should watch the same events but complete the observations independently.

Question 5

inter observer
interviews

Answer 5

Multiple people will interview the same people.

The questions to be asked will be agreed beforehand.

Notes are taken independently for each interviewer.

They will then compare their answers.

Question 6

inter observer
content analysis

Answer 6

Researchers will agree on behaviour categories beforehand.

They will then analyse the same content independently.

They then compare their findings.

Question 7

imporving reliability

questionaries

Answer 7

• A test which scores low on test-retest reliability (under +.8) may need some of the items deselected or rewritten
• Questions must not be ambiguous, complex or subjective.

Question 8

correlation coeffecient

Answer 8

The degree of correlation can be measured statistically using a statistical test with two sets of data

This calculates a correlation coefficient

For the results to be considered reliable, the coefficient needs to be above 0.8

Question 9

improving reliability

interviews

Answer 9

• The interviewers may have produced very different answers
• To try to prevent this, questions re-written to eliminate ambiguity

Question 10

improving reliability

observations

Answer 10

• Observers would go back through and review the behavioural categories
• They would make sure that behavioural categories used during the observations are properly operationalised (measurable and self-evident)
• Categories should not overlap and all possible behaviours should be covered on the checklist

Question 11

improving reliability

experiments

Answer 11

• Experiments are usually described as reliable
• bc of strict control over variables n conditions, n standardised instructions
• To improve reliability, the researchers need to ensure that the experiment is replicated precisely