Chapter 5

• Self report = people answer questions about themselves in a questionnaire or interview

              e.g. Dieners 5-item scale or ladder of life question
• Observational measure = recording observable behaviours or physical traces of behaviours
• Physiological measure = biological data
• Scales of variables:

  Categotical – categories (qualitiative)

  Ordinal – quantitative variable – ranked order

  Interval – ranked order with equal intervals

  Ratio – ranked order with equal intervals and a true 0
• Reliability = how consistent the results of a measure are
• Test-retest = Consistency in results every time a measure is used

  Most relevant for measuring theoretically stable constructs
• Interrater = The degree in which 2 or more coders/observers give consistent ratings of a set of targets

  Most relevant for observational measures
• Internal = Consistency of a pattern of answers

  Average inter item correlation
• Correlation coefficient can be used to quantify reliability
• Face validity = plausible operationalisation of the conceptual variable in question
• Content validity = extent to which a measure captures all parts of the defined construct
• Criterion validity = empirical form of measurement validity that establishes the extent to which a measure is associated with a behavioural outcome which it should be associated with

  • Important for self report – does it actually reflect real behaviour
  • Assessed with known groups paradigm (do scores match other groups whose behaviour has been confirmed )
• Convergent validity = empirical test of the extent to which a self-report measure correlates with other measures of a theoretically similar construct
•  Discriminant validity = empirical test of the extent to which a self-report measure does not correlate strongly with measures of theoretically dissimilar constructs