validity

• validity


  accuracy of research and its findings - extent to which an observed effect is genuine - two main types (internal and external validity)
• internal validity 


  whether the research measured what it intended to measure - how successful the study has been in trying to control extraneous and confounding variables
• external variables


  whether research findings can be generalised to outside world - whether the research is representative of people places and times out in real world

  ecological validity - generalises to real life settings and situations

  population validity - generalises to other people in target population

  temporal validity - generalises to other historical times and eras
• Assessing validity - face validity 


  whether test or measurement looks like it is measuring what the researcher intended to measure - assessing whether test items appear on the face of it to measure what the test claims to measure - can be done by simply eyeballing the measuring instrument or passing it to an expert to check - e.g. could assess a stress questionnaire for face validity by checking all questions look like they are obviously related to stress
• Assessing validity - concurrent validity

  extent to which a test or measurement produces similar findings to a recognised and more established test of the same topic - assessing whether current measurement produces results similar to previously validated measurement of same variables - can be done by giving participants both measures at same time and comparing scores - e.g. assess new IQ test for concurrent validity by comparing results from test with results the same participants got on an older more established IQ test to see if the scores correlate strongly
• improving validity 


  poor face validity (doesn't look like they're measuring what they're supposed to be measuring) - questions should be removed and/or rewritten so they relate more clearly and obviously to topic being measured

  low concurrent validity (scores don't correlate with those on the more established test of same topic) - questions should be removed, revised and/or rewritten so they can be tested again for concurrent validity again

  internal/external - changing methods, techniques and designs