validity + reliability

• internal validity

  the findings are accurate and the effects on the DV are caused by the IV, therefore, the study measures what it intends to measure (confounding variables have been controlled for and will not affect the results)
• researcher bias

  the researcher will directly or indirectly influence the result of the study, through the process of designing the study or through the way the research in conducted and analysed
• demand characteristics

  the participants unconsciously work out the aim of the study and act differently
• social desirability

  participants answer in way to make them look good 
• how to deal with issues of internal validity

  control for extraneous and confounding variables
• ways of assessing internal validity

  1. concurrent validity
  2. predictive validity
  3. face validity
  4. content validity
  5. construct validity
• concurrent validity

  validating a measure by comparing it with an established measurement that has a known validity. If similar results occur on both, then the new test is valid, if not, it will have to be redesigned and retested
• predictive validity

  the degree to which accurately forecasts a future outcome on a more broadly related topic. Whether or not the findings apply in different and more varied situations
• face validity

  least sophisticated, checks whether the test appears to measure what it claims to and is subjective. Tests where the purpose is clear even to naïve respondents are said to have this validity
• content validity

  this objectively checks the method of measuring behaviour is accurate and decided whether it is a fair test that achieves the aims of the study by asking an expert in that area to check the test is valid
• construct validity

  most sophisticated test of validity, looks at whether the overall results reflect the phenomena, checking the existing definition being studied and redesigned the test if it measures a different construct
• external validity

  whether the findings can be generalised, if the study paints a true picture of real-life behaviours and would apply to different places, times or people
• ways of dealing with issues of external validity

  1. Set more realistic tasks
  2. Have a more realistic setting
  3. Have a more representative sample
• ways of assessing external validity

  1. mundane realism
  2. ecological validity
  3. historical validity
  4. population validity
• mundane realism

  whether the study shows real-life behaviours as the tasks are ‘everyday’ usual occurrences
• ecological validity

  whether the study would apply to different settings due to the environment of the study
• historical validity

  whether the study would apply to different time
• population validity

  whether the study would apply to different people
• internal reliability

  the extent to which a test or measure is consistent within itself
• how to assess internal reliability

  split-half reliability
• split-half reliability

  involves splitting a participants test in half and seeing whether they get the same or similar scores on the two halves, if so, internal reliability is high
• external reliability

  the extent to which a test produces consistent results over several occasions on the same participant
• ways of assessing external reliability

  1. inter-rater reliability
  2. test-retest reliability
• inter-rater reliability

  two or more psychologists produce consistent results while observing the same behaviour, seen through a positive correlation of their data
• test-retest reliability

  testing and retesting the same participants over time, with the same test and comparing their scores, if results are the same, the test has high external reliability
• how to deal with issues of reliability

  1. standardisation
  2. accurate measuring tool - will it be interpreted differently, agree on coding system
  3. redesign questions
  4. train interviewer