VALIDITY CONCEPTUAL BASIS 1
Validity: the degree to which evidence and theory supports the
interpretations of the test scores entailed by the proposed uses of
the test (to what degree a test measures what it is supposed to
measure)
A measure itself is neither valid or invalid; the
interpretations of scores are valid or invalid (test that is
reliable > valid, not the other way around)
o Consideration of interpretations of scores not the items
and scores themselves.
Validity is a matter of degree (NO all or none, NO threshold),
strong or weak
Validity of a test’s interpretation is based on evidence and
theory
o Need for strong objective evidence (experience is not
strong evidence)
Importance of validity
When psychological measurements are constructed for serious
purposes, the measurements are meaningful and useful only
is they have acceptable validity for their intended purpose.
Without validity > measurements are scientifically
meaningless, harmful for the individual and for society.
Traditional
perspective:
distinguishes between
content, criterion and
construct validity
Contemporary
perspective: focus on
, VALIDITY CONCEPTUAL BASIS 2
construct validity (extent to which test scores can be
interpreted as reflecting a particular psychological construct) –
with five types of evidence
1. Test Content Validity: match between the actual content of
the test and the ccontent that should be included.
Items should form a representative and adequate sample of
the construct relevant content
Threats to Content validity:
o Irrelevant content in the construct: e.g. items or
questions irrelevant to the construct that is to be
interpreted.
o Construct is under-representation: a test should include
as much content as possible related to the construct.
o Time, fatigue, respondent’s attention etc. are also
constraints on the amount of content.
Face Validity: degree to which a measure appears to be related to
a construct based on the judgement of non-experts (respondents).
In some cases it is undesirable because respondents should
not know what the test measures.
2. Internal Structure Validity: the match between the actual
structure of a test and the structure that the test should have
according to the theory
Factor analysis > to investigate dimensions, factors, link
between items and factors, and match with theory
3. Response Process Validity: match between the psychological
processes that respondents actually use when completing a
measure and the processes that they should use.
Validity: the degree to which evidence and theory supports the
interpretations of the test scores entailed by the proposed uses of
the test (to what degree a test measures what it is supposed to
measure)
A measure itself is neither valid or invalid; the
interpretations of scores are valid or invalid (test that is
reliable > valid, not the other way around)
o Consideration of interpretations of scores not the items
and scores themselves.
Validity is a matter of degree (NO all or none, NO threshold),
strong or weak
Validity of a test’s interpretation is based on evidence and
theory
o Need for strong objective evidence (experience is not
strong evidence)
Importance of validity
When psychological measurements are constructed for serious
purposes, the measurements are meaningful and useful only
is they have acceptable validity for their intended purpose.
Without validity > measurements are scientifically
meaningless, harmful for the individual and for society.
Traditional
perspective:
distinguishes between
content, criterion and
construct validity
Contemporary
perspective: focus on
, VALIDITY CONCEPTUAL BASIS 2
construct validity (extent to which test scores can be
interpreted as reflecting a particular psychological construct) –
with five types of evidence
1. Test Content Validity: match between the actual content of
the test and the ccontent that should be included.
Items should form a representative and adequate sample of
the construct relevant content
Threats to Content validity:
o Irrelevant content in the construct: e.g. items or
questions irrelevant to the construct that is to be
interpreted.
o Construct is under-representation: a test should include
as much content as possible related to the construct.
o Time, fatigue, respondent’s attention etc. are also
constraints on the amount of content.
Face Validity: degree to which a measure appears to be related to
a construct based on the judgement of non-experts (respondents).
In some cases it is undesirable because respondents should
not know what the test measures.
2. Internal Structure Validity: the match between the actual
structure of a test and the structure that the test should have
according to the theory
Factor analysis > to investigate dimensions, factors, link
between items and factors, and match with theory
3. Response Process Validity: match between the psychological
processes that respondents actually use when completing a
measure and the processes that they should use.
