Criteria
for good measurement
The basic problem of scaling is the conversion of
qualitative data into quantitative one. The following are the procedures
included in the scaling.
· Have
thorough knowledge of the subject. This includes the ability to know what the
researcher wishes to measure. This step helps to determine the scalability of
the phenomenon under the study
· Decide
the characteristics of the respondents like age, sex, education, income,
location, profession etc
· Data Collection technique.
· Ensuring
goodness of measures that means the instrument developed to measure a
particular concept is indeed accurately
measuring the variable. i.e. we
Reliability
·
Stability and consistency
with which the instrument measures the concepts and helps to assess the
goodness of a measure.
· A
measure is considered reliable if it would give the researcher the same
result over and over again.
·
Reliability is measured in two forms
§ Stability
of a measure is the ability of a measure to remain the same over time
§ Two
types of stability reliability
·
Test-retest reliability
·
Parallel-form reliability
§ Inter
item consistency reliability
· This
is a test of the consistency of respondents’ answers to all the items in a
measure.
· To
the degree that items are independent measures of the same concept, they will
be correlated with one another.
· The
most popular test of inter item consistency reliability is the Cronbach’s
alpha, 1946, which is used for multipoint-scaled items and the
Kuder-Richardson Formular, 1937, used for dichotomous items.
· The
higher the coefficients, the better the measuring instrument.
§ Split-half
reliability
· Split-half
reliability reflects the correlations between two halves of an instrument.
-------------------------------------------------------------------------------------------------------------------------
Validity of the research( Dudovsky, 2018)
· It
relates to the extent at which the survey measures right elements that need to be measured.
· It shows the degree to which an instrument
measures what it is intended to measure.
· There are two divisions of validity namely
internal validity and external validity.
§ It is also known as logical validity or Face
validity.
§ It
is used to know whether or not the study or test measures what it is supposed
to measure.
§ Content
validity ensures that the measure includes an adequate and representative set
of items that tap the concept. It is a function of how well the dimensions and
elements of a concept have been delineated.
§ it
is weakest form of validity
§ For example, IQ tests are supposed to measure intelligence.
The test would be valid if it accurately measured intelligence. Thus, a test
can be said to have face validity if it "looks like" it is going to
measure what it is supposed to measure.
§ Content validity is the extent to which an instrument
provides adequate coverage of topic under study. It can also be determined by
using a panel of persons who shall judge how well the measuring instruments
meets the standards.
§ It relates to the ability of the instrument to predict some
outcome or estimate the existence of some current condition.
§ The degree to which a measurement can accurately predict
specific criterion variables. It can tell us how accurately a measurement can
predict criteria or indicators of a construct in the real world.
§ It
measures how well one measure predicts an outcome for another measure. This
test is useful for predicting the performance or behaviour in another situation
(past, present or future). Example, A job
applicant takes an entry test during the interview process. If this test
accurately predicts how well the employee will perform on the job, the test is
said to have criterion validity. The first measure (Entry test) is called the
predictor variable or estimator. The second measure (future performance) is
called criterion variables as long as the measure is known to be a valid tool
for predicting outcomes.
§ Types of criterion related validity
·
Predictive
validity
·
Concurrent validity
When the predictor
and criterion data are collected at the same time, it can also refer to when a
test replaces another test (i.e. because its cheaper). For example, a written driver’s test replaces an in-person test
with an instructor.
§ It
relates to the assessment of suitability of measurement tool to measure the
phenomenon being studied.
§ The
degree to which a test measures what it claims to be measuring.
§ Shows to whether a scale or test measures the construct
adequately.
§ Construct (Variable) is actually an idea that is to be
translated into concrete through operationalization process. Construct validity
refers to whether the operational definition of a variable actually reflect the
true theoretical meaning of a concept.
§ It is a test of generalisation like external validity, but
it assesses whether the variable (construct) that are being tested for is
addressed by the experiment. For example, you
might design whether an educational program increases artistic ability amongst
pre-school children. Construct validity is a measure of whether your research
actually measures artistic ability, a slightly abstract label.
§ Subcategories of construct validity are convergent validity
and discriminant validity.
·
Convergent
validity
The degree to which a measure is correlated with other measures that it is theoretically
predicted to correlated with
· Discriminant validity
Tests whether concepts or measurements that are supposed to be unrelated
are, in fact, unrelated.
In the above example, based on theory, there are
two different constructs namely self esteem and locus of control having 2 items
each. Here there is discriminant
validity as the relationship between measures from different constructs is very
low. It can be said that the two sets of measures are discriminated from each
other.
-------------------------------------------------------------
Understanding Reliability and Validity
No comments:
Post a Comment
Share your ideas