Measurement of behavior

Measurement of behavior

1. scales of measurement

   • nominal
     • numbers assigned are labels. for example: male is 1, female is 2
   • ordinal
     • rank ordering of a set of behaviors or characteristics
   • interval
     • equal differences between the numbers reflect equal differences between participants in the characteristic being measured: IQ tests
   • ratio
     • highest level of measurement. has a zero point: 0 cm, 0 seconds

2. assessing the reliability of a measure

   • measurement error
     • observed score = true score + measurement error
     • transient states
       • state of the participant, affects the measurement error
     • stable attributes
       • paranoid or suspicious participants may purposefully distort their answers
     • situational factors
     • characteristics of the measure
     • mistakes
   • reliability = true score / true variance
   • type of reliability
     • correlation coefficient
       • describes the strength of the relationship between the 2 measures
     • test-retest
       • multiple tests over time
     • interitem reliability
       • relevant for measures that consist of more than one tiem. degree of consistency among the items on a scale
     • split-half reliability
       • the researcher divides the items on the scale into 2 sets. total score for each set, then correlation between both sets
     • cronbach's alpha coefficient
       • is equivalent to the average of all possible split-half reliabilities
     • increasing the reliability of measures
       • standardize administration of the measure
       • clarify instructions and questions
       • train observers
       • minimize errors in coding data

3. assessing the validity of a measure

   • validity refers to the extent to which a measurement procedure actually measures what it is intended to measure
   • types of validity
     • face validity
       • refers to the extent to which a measure appears to measure what its supposed to measure
     • construct validity
       • we asses construct validity by seeing whether a particular measure relates as it should to other measures
       • hypothetical contructs
         • entities that cannot be directly observed but are inferred on the basis of empirical evidence
     • convergent validity
       • measure should correlate with other measures
     • discriminant validity
       • does not correlate with measures that it shouldnt correlate
   • criterion-related validity
     • refers to the extent to which a measure allows us to distinguish among participants on the basis of a particular behavioral criterion
     • concurrent validity
       • 2 measures are administered at roughtly the same time
     • predictive validity
       • refers to a measure's ability to distinguish between people on a relevant behavioral criterion at some time in the future