Meta-Analysis

• Meta-analysis is when a researcher looks at the findings from a number of different studies and produces a statistic to represent the overall effect.
• Effect size

  Quantitative measure of the difference between conditions.
• Meta analysis produces an effect size of the DV in order to assess overall trends.
• Uses secondary data
• Kohnken et al (1999)


  Used meta-analysis of 53 studies, on cognitive interview and standard police interview. There was a 34% increase in recall with the cognitive interview technique. (34%= Effect size)
• Anderson et al (2010)


  Used meta-analysis of 136 studies including correlational, experimental and longitudinal research studies. Exposure to video game violence could therefore be associated with increased aggressive behaviours.

  This was true of males and females and across individualistic and collectivist cultures.
• Van Ijzendoorn and Kroonenberg (1988)


  Meta-analysis of 32 studies from 8 different countries including: UK, China, USA, Israel... to explore types of attachment. There were 2000 strange situations classifications. It found that type 2 (secure attachment) was the most common across different cultures.
• Strengths:

  • Cheap
  • Quick to collect data
  • Can see trends
  • Minimises impact of anomalies
  • Population validity
  • Overall conclusions
  • Universalistic behaviours can be identified
  • Easy access to secondary data
• Weaknesses:

  • Not truly comparable
  • Not personally aware of the internal validity of data.