validity Flashcards
what is validity?
● validity refers to whether an observed effect is genuine and represents what is actually ‘out there’ in the real world
● the legitimacy of results
what are the different types of validity?
● internal validity
● external validity: ecological validity and temporal validity
what is internal validity?
refers to how well study (procedure) has measured what it sets out to measure at start of research
how is internal validity increased?
● if there is lots of control implemented in the procedure
● allows researcher to simply measure what they set out to in their aim and doesn’t allow any other variables to impact upon that
what is external validity?
refers to the extent to which findings of a study can be generalised to factors outside of research
what are the two types of external validity?
● ecological validity
● temporal validity
what is ecological validity?
refers to whether task and/or setting reflects real life situations and can therefore be applied/generalised to real life situations
what is temporal validity?
refers to extent to which findings from a research study can be generalised to other historical times and eras (i.e. do findings remain true over time)
what are the different ways of assessing validity?
● face validity
● concurrent validity
what is face validity?
● refers to extent to which something looks as if it will measure what it is supposed to measure
● can be achieved by ‘eyeballing’ the measuring equipment or by passing it to an expert to check
● for example, on a questionnaire about aggression, whether the questions are obviously related to aggression
what is concurrent validity?
● refers to extent to which a test correlates well with a measure of the same thing that has been previously validated
● to assess this, you would compare results of new measure with a previously validated measure
● for example, compare results of new intelligence test with results of a previously validated measure of intelligence (participants complete both tests)
how to improve validity of experiments?
● having controlled procedure means researcher is more certain that the changes in DV were due to the effects of IV
● controls could include:
a control group
single / double blind procedure
randomisation
how to improve validity of questionnaire?
● filler questions control for effects of social desirability bias
● also, if respondents know their data is confidential, they are also more likely to be truthful
how to improve validity of observations?
behavioural categories should be well defined and thoroughly operationalised to reflect behaviours being measures
