Psychometric tests Flashcards
Charles Darwin
despite similarities, marked individual differences are normal
why are individual differences normal
some of the individual differences are more adaptive than others
- over time the differences lead to more complex, intelligent organisms
psychometrics
the field of study concerned with the theory and practice of psychological measurements (intelligence and personality)
psuedosciene
according to karl popper- tries to explain the differences in personality
e.g. the shape of someones face giving detail on personality
personality
- underpinned traits
- changes over lifespan- very slowly
concepts of psychometric tests
- reliability
- validity
reliability
the degree to which a test or measure process the same scores when applied in the same circumstances (Nelson, 1997)
tests that are accurate would be
measured the same by a different person
traits usually change very slowly over time
used to measure personlity
types of reliability
internal and external
internal
extent to which a measure is consistent within itself
external
the extent to which a measure varies from one use to another
internal: split half method
measure the extent to which all parts of the test contribute equally to what is being measured
external: (2)
test re-test and inner-rater
external: test re-test
measures the stability of a test over time
- however some dependent variables are in their nature highly variable
external: inter-rater
to the degree to which different rater give consistent estimates of the same behaviour
- two different people using the same scale should get the same answer
Validity
degree to which a test of instrument measures what it purports to measure (Thomas and Nelson, 1996)
-does it really measure what you think it measure?
Types of validity (2)
- content-related
- criterion-relation
validity: content-related
appropriate content
validity; criterion-related
relationship to other measures
Content related : face validity
does the test appear to test what it aims to test
Content related: construct validity
does the test rate to underlying theoretical concepts
criterion-related: concurrent validity
does the measure relate to an existing similar measure
criterion-related: predictive validity
does the test predict later performance on a related criterion
on a dart board if all the darts landed in the same area but not on bulls eye
reliable
not valid
on a dart board if all the darts landed all over the board
low reliability
low validity
if all the darts land on bulls eye
both reliable and valid