Validity and Reliability Flashcards
Reliability
- Reliability refers to whether something is consistent.
- Any tool used to measure something must be reliable.
- The reliability of an experiment can be determined through replication and often leads to replication.
What is a type of reliability?
Inter-observer/inter-rater reliability
Inter-observer /inter-rater reliability
Inter-observer reliability refers to the extent to which there is agreement between 2 observers involved in observing a behaviour.
Validity
- The results of a research may be reliable but this does not necessarily mean that they are valid.
- Valid results are true and accurate.
What are the 2 main types of validity?
- Internal validity
- External validity
Internal validity
- The extent to which a study actually measures what it claims to be measuring.
- Internal validity can be established through control of relevant extraneous variables in an experimental design so that they don’t become confounding variables, using a repeated measures design, controlling situational and investigator variables, attempting to reduce demand characteristics and social desirability bias.
What are the 2 main types of internal validity?
- Face validity
- Concurrent validity
Face validity
Whether a test appears to measure what it claims to at face value.
Concurrent validity
Comparing the results obtained by a new test with an established one to see if they produce similar results.
External validity
- Even though a research study has internal validity, it does not mean that its findings can be generalised.
- External validity refers to the extent to which findings can be generalised beyond the study.
- External validity can be established through the sampling, partial replication, realism and triangulation.
What are the 4 main types of external validity?
- Ecological validity
- Population validity
- Temporal validity
- Predictive validity
Ecological validity
- Whether findings can be generalised to real-life settings. It includes:
- Generalisability - ability to generalise findings outside the lab.
- Representativeness/Mundane Realism - how well a study’s tasks or procedures reflect real-life situations.
Population validity
- Whether findings can be generalized to different groups of people.
Temporal validity
- Whether findings remain relevant over time.
Predictive validity
How well a test or measure can predict future outcomes.
