Validity Flashcards
define validity
the extent to which am observed effect is genuine
r we measuring what we intended to?
internal validity
does it measure what it was supposed to measure
external validity
can it be generalised beyond the research setting which it was found beyond context
threats to internal validity
extraneous variables
confounding variables
demand characteristics
investigator effects
leading questions
social desirability bias
what’s another word for temporal validity?
historical validity
define temporal validity
extent to which behaviours observed/recorded in a study can be generalised to other historical periods
example of temporal v
Asch + high rates of conformity might be to do with conformist era in USA history
ecological validity
extent to which behaviours observed/recorded in a study reflect the behaviours that actually occur in the real world
acsh - artificial task so low ec val but described processes we see in everyday life so acc high ec val and has mundane realism
how do you assess validity?
face and concurrent validity
define face validity
extent to which test items look like what the test claims to measure
one or more judges asses weather the test seems appropriate + suggest charges if necessary
define concurrent validity
-means of establishing validity by comparing an established existing test or questionnaire with the one you r interested in.
-new measure test scored r correlated with those from established valid test
-low correlation = change test
How to improve validity (experimental)
-use a control group so researcher can assess changes in dv r due to iv
-standardise procedures to minimise impact of participant reactivity/investigator effects
-use of single/double bind procedures = reduce demand characteristics as single - they only know aims once taken part
How to improve validity (questionnaires)
-lie scale - set qs to see if truthful + control social desireabillity bias
-telling participants they can be anonymous
How to improve validity (observations)
-use covert observations to increase ecological validity
-have clear behavioural categories that don’t overlap
How to improve validity (qualitative methods)
-more in depth + in detail data
-triangulation (using different sources)
-interpretive validity (including quotes + consequences)