reliability

Question 1

what is reliability

Answer 1

refers to how consistent the findings from an investigation or measuring device are .

Question 2

two ways of assessing reliability

Answer 2

test-retest reliability
inter-observer reliability

Question 3

test-retest method

Answer 3

-a method of assessing the reliability by administrating the same test or questionnaire to the same person on different occasions
-if test or questionnaire produces similar results(consistent) or the same each time then the results are reliable
-mostly used for questionnaires, IQ tests, can also be applied to interviews

Question 4

what must the researcher do when using the test-retest method

Answer 4

there must be sufficient time between the test and retest so that the respondent hasn’t memorised the answers or their attitudes, opinions and abilities haven’t changed

Question 5

how will the researcher measure to see if the results are similar

Answer 5

-the two sets of scores would be correlated to make sure they are similar
-if the correlation turns out to be significant(+0.8 and above)then the findings are high in reliability

Question 6

inter-observer reliability

Answer 6

the extent to which there is an agreement between two or more observers involved in observations of behaviour.
-this agreement is measured by correlating the observations of two or more observers
-if the value of the correlation co-efficient is +0.8 or above then the data is reliable

Question 7

how does inter-observer reliability become established

Answer 7

-may involve carrying out a pilot study of the observation = check that observers are are applying behavioural categories in the same way .

Question 8

what happens if there is only one researcher observing

Answer 8

observer bias may take place as their interpretation and opinions may influence what they perceive and record in the observation=the researcher is introducing subjectivity, bias and unreliability to the data collection process

Question 9

improving reliability in a questionnaire

Answer 9

-using the test-retest method
-comparing two sets of data that should produce a correlation of 0.8
-a questionnaire that produces low test-retest reliability may require some of its questions to be rewritten or deselected
-replace open questions with closed questions(less room for misinterpretations and ambiguity

Question 10

improving reliability in interviews

Answer 10

-use the same interviewer each time, if this is not possible or practical all interviewers must be trained=avoid asking leading questions
-use structured interviews=interviewers behaviour is more controlled by fixed questions

Question 11

improving reliability in experiments

Answer 11

-use lab experiments=researcher can exert strict controls over the conditions the participants are tested in.
-making sure participants are tested under the same conditions each time they were tested

Question 12

improving the reliability in observations

Answer 12

-making sure behavioural categories are operationalised =the categories will not overlap =the observers will not make their own judgement of what to record =inconsistent findings