Reliability and Validity Flashcards
what is reliability?
refers to how much we can depend on any particular measurement and how much we can
repeat the same study and get the same result.
external reliability
the ability to replicate the results.
Can be assessed replicating test and
the correlation between two scores.
internal reliability
the consistency of a measure within a test. Its typically assessed using the
split-half method
Inter-rater reliability
the degree to which different rates/observers give consistent estimates of the same object
Test-retest reliability
same test is given to the same sample on two different occasions.
Ways to improve reliability
Take more than one measurement from each participant (reduces impact of anomalies)
• Use pilot studies to check proposed method works properly.
• When using more than one investigator, the ways they collect and record data should be
standardised to improve inter-rater reliability
• Checking data carefully when its recorded and written down.
validity
whether or not a study is measuring what it is supposed to measure.
external validity
how well the results can be generalised beyond the study itself and
generalised to other populations (population validity) or other settings (ecological validity)
internal validity
the ability of the study to test the hypothesis that it was designed to test.
face vailidity
a judgement about whether a test seems to be valid.
content validity
asking an expert in the field to assess and see if the study is an accurate measure
Construct validity
assess how close the study relates to underlying theoretical constructs
Concurrent validity
whether the test shows similar findings to another existing
measure, for example take another measure from the same participant and compare the two sets of data.
Predictive validity
how well a test predicts future performance