reliability

Question 1

reliability

Answer 1

Consistency – a measurement made twice should produce similar results each time (correlation coefficient of +.8 or more).

Question 2

2 ways of assessing reliabilty

Answer 2

test-retest, inter-observer

Question 3

test-retest

Answer 3

A test/questionnaire used on two occasions is reliable if it produces similar outcomes/scores each time.

Question 4

inter-observer

Answer 4

Two observers of the same behaviour make reliable observations if they interpret the behaviour in the same way (also inter-interviewer and inter-rater).

Question 5

improving questionnaires and interviews reliability

Answer 5

Rewrite or remove ambiguous questions, use more closed questions, use structured interviews, train interviewers.

Question 6

improving observations reliability

Answer 6

Operationalise behavioural categories, avoid overlapping, train observers, discuss decisions.

Question 7

improving experiment reliability

Answer 7

use standardised procedures