Validity & Reliability Flashcards
(Validity & Reliability) How do you check for test-reset reliability?
Repeat the study with the same participants (to see if the same results are obtained the second time).
(Validity & Reliability) How do you check for inter-rater reliability?
Check one observer’s findings against those of another observer (to see if they are consistent with each other).
(Validity & Reliability) How do you check for spilt-half reliability?
Compare items within a test to see if they are giving the same findings (e.g. compare odd-numbered items with even-numbered items.
(Validity & Reliability) What are the 4 ways to improve reliability?
- Make the procedure standardised.
- Make the study replicable.
- Make the sample large enough.
- Ensure questionnaires contai multiple items all related to the same construct.
(Validity & Reliability) Ways to improve reliability: Why would you standardised the procedure?
So that all participants have the same experience.
(Validity & Reliability) Ways to improve reliability: Why would you make the study replicable?
To be able to check that the original study was reporting an effect that will be consistently seen).
(Validity & Reliability) Ways to improve reliability: Why would you make the sample large enough?
To reveal the typical, consistently occurring response (i.e. that has not been distorted by flukes or anomalies).
(Validity & Reliability) Ways to improve reliability: Why would you ensure that the questionnaires contain multiple items all related to the same construct?
To be able to find out a participant’s ‘settled’ response.
(Validity & Reliability) Describe face validity.
Whether, on the face of it, the test looks like it is measuring what is supposed to be measured.
(Validity & Reliability) Describe construct validity.
Whether the test has been shown to measure what it is supposed to be measuring (i.e. the desired construct).
(Validity & Reliability) Describe concurrent validity.
Whether results on one test concur with results on another tests (such as measuring the same construct).
(Validity & Reliability) Describe criterion (predictive) validity.
Whether results on a test can predict results on other (similar) tests in the future.
(Validity & Reliability) Describe ecological validity.
Does the study represent a real-life situation?
(Validity & Reliability) Describe population validity?
Can the sample be generalised from?
(Validity & Reliability) List the 4 types of internal validity.
Face, construct, concurrent and criterion (predictive).