reliability and validity

• what is reliability?

  the extent to which research findings are consistent, and therefore dependable
• what is internal reliability?

  whether items within a questionnaire or test are consistent within themselves
• what is external reliability?

  whether a questionnaire or test produces consistent results over time or in different situations
• what is inter observer reliability?

  the degree to which different observers give consistent recordings of the same behaviour
• how is internal reliability assessed?

  the split half method
• what is the split half method?

  measuring consistency within a test by comparing a person's performance in halves on the same test
• how is external reliability assessed?

  the test re-test method
• what is the test re-test method?

  administering the same test to the same person at a different time
• how is inter observer reliability assessed?

  observing in teams of 2, watching the same event, and recording observations separately
• what is validity?

  the measure of legitimacy and whether the test measured what it set out to
• what is ecological validity?

  whether both the setting and the test takes place in and the task have mundane realism (a type of external validity)
• what is internal validity?

  how much the findings of the dependent variable actually have to do with the manipulation of the independent variable and not other factors
• what is temporal validity?

  whether results from a study or concepts within a theory remain true and valid over a period of time
• how is internal validity assessed?

  1. face validity
  2. concurrent validity
• what is face validity?

  an independent expert 'eye-balls' the measure being used and assesses whether it will measure what it's set out to (an intuitive measurement)
• what is concurrent validity?

  comparing the new procedure with a similar procedure that's been done before, where validity has already been established