Reliability

Question 1

A01

Outline reliability

Answer 1

Reliability is a measure of consistency
if a measurement is repeated and produces same result then the measurement is reliable

Question 2

Outline the ways of assessing reliability

Answer 2

• Test-retest
• Split-half method
• Correlating inter-observer reliability

Question 3

A01

Outline the test-retest method

Way of assessing reliability

Answer 3

Involves administering the same test to same person/ppl on different occasions
If the result obtained are same or similar both times, the test is said to have external reliability
* test-retest method is commonly used with Questionnaires, IQ tests & interviews

Question 4

Define external reliability

Answer 4

Is when a test or study should consistently produce the same results no matter the time given

Question 5

Outline the split-half method

Way of assessing reliability

Answer 5

The split-half method is used to assess the internal reliability of a test
Split-half method takes one test & divides it into two sections
Can be even/odd numbered Qs or first/second half
If there is a strong positive correlation between both halves-the test is said to have internal reliability
so if p scores similar results in both sections of the test

Question 6

Define internal reliability

Answer 6

Is looking at the same test & asking do all parts of the test have consistent results?

Question 7

Outline inter-observer reliability

ways of assessing reliability

Answer 7

Is the extent to which there is an agreement between 2 or more observers involved in observations of a behaviour
To test for inter-observer reliability, tests from different researchers are correlated to check if the results have a high positive correlation
this may involve a small scale trial run( pilot study) of the observation in order to check that observers are applying behavioural categories in the same way
Observers need to watch same event, but record their data independently
The data correlated by the two observers should be correlated to assess its reliability

e.g if both researchers observed behaviour & gave same score of 10 then test has inter-observer reliability

Question 8

A01

Outline the ways of improving reliability for Questionnaires

Answer 8

Reliability of questionnaires should be measured using test-retest method
Comparing 2 sets of data should produce a correlation that exceeds +.80
If the Questionnaire produces low test-retest reliability then should deselect some items/rerite them
as comples open Qs may be interpretted differently
solution-replace open Qs with closed fixed choices that are less ambiguos

Question 9

Outline the ways of improving reliability for Interviews

Answer 9

To esnure reliability for interviews use same interviewer each time
All interviewersw should be trained to avoid leading Qs
use structured interviews as leading Qs can be avoided & interviewers behaviour is controlled by fixed question
as unstructured are unreliable

Question 10

Outline the ways of improving reliability for experiments

Answer 10

Use lab experiments as can exert coontrol over aspects of procedure such as instructions given to P & conditions in which they are tested
can replicate experiment

Question 11

Outline the ways of improving reliability for Observations

Answer 11

For observations reliability can be improved by ensuring behavioural caterogires are operationalised & measurable
Categories should not overlap ( i.g ‘hugging’ & ‘cuddling’)
If categories are not operationalised researcherd will produce inconsistent results