Validity Flashcards
What are the 2 types of validity?
Internal
External
What is internal validity?
The extent to which a test measures what it’s supposed to be measuring.
The extent to which results / DV are solely affected by the IV.
What is external validity?
The extent to which the results of a test generalises beyond the scope of research.
What are the types of external validity?
Ecological
Temporal
Population
What are ways of assessing validity?
Concurrent validity
Face validity
What is ecological validity?
Extent to which findings can be extrapolated / generalised / applied to everyday life.
What is mundane realism?
Extent to which the task/procedure in an experiment are similar to real-life everyday events.
What is temporal validity?
Extent to which findings can be generalised / applied across time frames.
What is population validity?
Extent to which findings can be generalised to the wider population.
What is concurrent validity?
Method of assessing validity -
when results of a test is compared with the results of a VALIDATED test in a similar field of research.
What is face validity?
Method of assessing validity -
asking, ‘does the test APPEAR to measure what it says it measures?’
How would you improve the validity of an experiment?
Conduct a lab experiment with controlled EVs.
Single-blind or double-blind procedures =
Reduces demand characteristics / investigator bias.
Standardised procedures =
minimises investigator effects.
How would you improve the validity of a questionnaire?
Researchers would include a LIE SCALE =
to check the consistency of pps responses.
E.G. having 2 questions that ask the same thing but in opposite ways.
Making questionnaire anonymous =
Less social desirability bias - more truthful.
How would you improve the validity of an observation?
Covert/Structured observation =
Can increase ecological or internal validity.
Behavioural categories =
Reduces chance of observer bias / subjectivity - categories are CLEARLY DEFINED / OPERATIONALISED.
Triangulation =
Having data coming from interviews, observation and written reports from pps - comparing the data.