Reliability

Question 1

What is reliability?

Answer 1

Refers to the consistency of a test or procedure

Question 2

What are the ways of assessing reliability?

Answer 2

test-retest method and inter-observer reliability

Question 3

What is the test-retest method?

Answer 3

The experiment/questionnaire/test/scale is carried out initially and then at a later date (not too soon or too much later) the thing is repeated with the same group of participants - the two sets of data are compared

Question 4

What is inter-observer reliability?

Answer 4

Observations should always be carried out by at least two researcher - and their observations must be consistent between themselves. Observers should decide on behavioral categories together and conduct a small scale pilot study and then compare their findings. This data is compared and the correlation coefficient should exceed +0.8 before the observation can proceed.

Question 5

How can you improve the reliability of questionnaires?

Answer 5

Replace some of the open questions with closed questions which may be less open to interpretation

Question 6

How can you improve the reliability of interviews?

Answer 6

Use the same interviewer each time

Ensure the interviewer is trained (eg so they don’t ask leading or ambiguous questions)

Question 7

How can you improve the reliability of experiments?

Answer 7

Ensure participants are tested under the same conditions each time they’re tested

Question 8

How can you improve the reliability of observations?

Answer 8

Ensure behavioral categories are full operationalised and that they don’t overlap and that all possible behaviors are included on the list