validity

• What threatens internal validity?

  Extraneous variables

  • don’t vary systematically with the IV but may still have an effect on the DV. Make it difficult to detect specific effect.

  Confounding variables

  • is not the IV but varies systematically with the IV, So changes in DV may be due to confounding variables and not the IV so the outcome is meaningless
• Describe two ways of assessing and improving internal validity

  • Face validity- the extent to which the test items look like what the test claims to measure. Improve- questions should be revised so they relate more obviously to one topic
  • Concurrent validity- when you compare an established test/questionnaire which claims to measure the same variable with the new method. Any positive correlation should be gained between the results of the two tests. Improve- remove questions which may seem irrelevant
• what is internal validity?

  The degree to which an observed effect is due to experimental manipulation rather than confounding/extraneous variables
• state 3 ways of reducing participant variables

  • matched pairs
  • repeated measures
  • random allocation
• state a way of reducing situational variables

  • standardise procedures
  • make sure study takes place at same time of day, in same place, etc
• how can you reduce demand characteristics?

  • single blind trial
• How can you reduce investigator effects?

  • double blind
  • standardise procedures/instructions
• How can we reduce participant effects like social desirability bias and the Hawthorne effect?

  • social desirability- ensure confidentiality of participants will be put in place
  • Hawthorne effect- ensure experimental realism- eg sufficiently engaging with pps so they focus on the task and don't pay attention to the fact they are being observed
• what is external validity?

  degree to which experimental findings can be generalised to other settings to different groups of people over time
• what is ecological validity?

  a form of external validity, ability to generalise a research effect beyond the setting it's demonstrated in to real life
• what is temporal validity?

  ability to generalise research findings beyond a particular time period
• how can order effects be controlled?

  use counterbalaning
• what are the three types of external validity, how are they assessed?

  • population validity- when findings can be generalised to a larger group of people. Assessed by analysing how the results can be applied to groups of people other than study sample
  • Temporal validity- findings can be generalised to time periods beyond that of the study. Assessed by repeating experiment in different time periods
  • Ecological validity- experimental effect can be generalised to settings in every day life/reality. Assessed by assessing control of investigation and the test materials used- are they too artificial?