Reliability across all methods of investigation

• Define reliability

  • A measure of the consistency of data
  • If a particular measurement is repeated and the same result is obtained then the measurement is said to be reliable
• Describe how test-retest can be carried out

  • Same test or questionnaire is given to the same person or people on two or more occasions
  • if the test or questionnaire produces the same or similar results each time then it’s reliable
• Explain what is meant by inter-observer reliability

  • Involves comparing observations from different observers
  • In a study two or more observers compare their data by conducting a pilot study
  • This is a small-scale trail run of a study and inter-observer reliability can be sued check that observers are applying behavioural categories in the same ways
• Describe how inter-observer reliability can be carried out

  • Observers should watch the same event
  • BUT record their data independently
• Describe how reliability is a measure of correlation

  • In test-retest and inter-observer reliability the two sets of scores are correlated
  • The correlation co-efficient should exceed +80 to show reliability
• Describe how improving questionnaires can improve reliability

  • A questionnaire which show low test-retest reliability may require some items to be deselected/ removed and some to be rewritten
  • The researcher could replace some open questions which might have been misinterpreted with close fixed questions that are less ambiguous
• Describe how improving interviews could improve reliability

  • Is to use the interviewer each time
  • if that’s not possible then all interviewers must be trained in the same way
  • To avoid questions that are leading or ambiguous
• Explain how standardised procedures in experiments can improve reliability

  • Lab experiments often involve standardised procedures and are often described as reliable
  • They have strict control over many aspects of the procedure
  • E.g. instructions the participants receive and conditions they’re placed in
• Explain how operationalisation of behavioural categories can improve reliability

  • Behavioural categories should be measurable and not subjective/ open to interpretation - pushing more easily measured than aggression
  • Behavioural categories should not overlap e.g hugging and cuddling
  • All possible behaviours should be included in category
• Explain why operationalisation of behavioural categories is important

  • If categories are overlapping or absent different observers have to use their own judgement when deciding what to record
  • Thus may lead to inconsistent records