Experimental designs

• Experiments

  • Experiments allow us to study cause and effect (causation). 
  • They all have an IV and a DV and make some attempt to control all other potential extraneous variables (EVs).
  • There are four different kinds of experiments
  • Lab experiments
  • Natural Experiments
  • Field experiments
  • Quasi-experiments
• Laboratory Experiments

  • Conducted in highly controlled environment
  • Does not have to be in a lab, could be in a classroom or anywhere else where conditions can be controlled.
• Strengths

  • High levels of control
  • High internal validity
  • Replication is more possible than in other types of experiments
  • This is important because we need to be able to check that the results of the study are not just a one off
• Weaknesses

  • Participants are aware they are being tested which may raise ‘unnatural behaviours’ (demand characteristics)
  • Task does not represent real-life experience - low mundane realism.

  May lack generalisability
• Field Experiments

  • The IV is manipulated in a more natural
  • More every day setting
• Strengths

  • High mundane realism (natural environment)
  • Behaviour may be more valid and authentic
• Weaknesses

  • Loss of control of extraneous variables
  • Replication may not be possible
  • Ethical issues of participants are not aware they are being studied
• Natural Experiments

  • A research takes advantage of a pre-existing IV. Natural because the variable would have changed even if the experimenter was not interested.
  • The IV is natural, not the setting.

  Example: Hodges and Tixard’s attachment research (1989)

  • Compared the long term development of children who have been adopted, fostered, or returned to their mothers with a control group of children who had spent all their lives in their biological families.
• Strengths

  • Opportunities for research that may not otherwise be undertaken for ethical reasons
  • High external validity (involves real-life issues)
• Weaknesses

  • A naturally occurring event may happen very rarely, reducing opportunity for research
  • Limited generalisability
  • Participants may not be randomly allocated to experimental conditions. So researcher may not be sure whether the IV affected the DV.
• Quasi Experiments

  • Have an IV based on existing difference between people (example: age or gender). No one has manipulated these variables (it simply exist)

  Example: Anxiety and Phobias

  • To compare anxiety level of a phobic and non-phobic patient
  • Having a phobia or not would not come about through any experimental manipulation
• Strengths

  • Carried out under controlled conditions therefore same strengths as lab experiment
• Weaknesses

  • Can’t randomly allocate participants to conditions 
  • therefore , may be confounding variables