Pilot Studies and Experimental Design

• Pilot studies


  small scale prototypes of a study that are carried out in advance to the full research to identify any problems with the: experimental design, instructions for participants, measuring instruments
• experimental design


  do the participants have enough time to complete the tasks?
• instructions for participants 


  are the instructions clear?
• measuring instruments 


  including the behavioural categories in observational research and questions when using questionnaires. They allow for categories and questions to be checked and modified where necessary
• Three types of experimental design

  • repeated measures
  • independent groups
  • matched pairs
• Repeated measures 


  where the same participants take part in each condition of the experiment. The data obtained from both conditions is then compared for each participant to see if there was a difference
• Independent measures 


  uses two separate groups of participants. They should be allocated to their group by random allocation which ensures that each P has an equal chance being assigned to one group or the other. This is important in reducing investigator effects and the influence of individual differences
• matched pairs 


  pairs of participants are matched from the sample, in terms of key variables such as age or IQ
• strength of repeated measures

  fewer participates are required, so this is less costly and time consuming. Reduces P variables as the same P's take part I.both/all conditions
• strengths of independent 


  avoids order effects and reduces demand characteristics making the results more valid
• strength of matched pairs

  avoids order effects and reduces participant variables and demand characteristics, making the results more valid
• Weakness of repeated 


  issues with order effects, such as practice effects or fatigue, as P's take part in both conditions
• weakness of independent 


  more participants are required and participant variables may affect the results
• weaknesses of matched pairs

  impossible to match people exactly, unless using identical twins. More P's are also required