ASSESSING

• WHAT IS RELIABILITY?

  extent procedures, research tools and findings are consistent
• HOW CAN RELIABILITY BE ASSESSED?

  • test-retest reliability
  • inter-rater reliability
• TEST-RETEST RELIABILITY?

  • questionnaires, psychological studies, interviews
  • method carried out twice
  • with duration of time between
  • before results compared
  • first and second scores correlated using statistical test
  • if correlation coefficient +0.8 or more the results are reliable
• CONDITIONS OF THE DURATION FOR TEST-RETEST RELIABILITY?

  • long enough that the answers are not just recall
  • short enough that the participant attitudes/ ability have not changed
• INTER-RATER RELIABILITY?

  • checking consistency of ratings completed by two or more independent researchers
  • "inter-observer" reliability for observations
  • content analysis
  • result consistency assessed using statistical test (e.g. spearman's rho)
  • if correlation coefficient is +0.8 or more then the behavioural categories are reliable