Criteria of Measurement Quality

CRITERIA OF MEASUREMENT QUALITY
• We began with assertion that social scientists can measure anything that
exists.
• We learned that there are things , that cant be measured , then we

learnt , it’s possible to measure them anyway.
• Yardsticks against which we judge our relative success or failure in

measuring things— even things that don’t exist.
Can you hit the bull's-
eye?
Three
targets with
three
arrows each
to shoot.
Both Precise Neither
How do
accurate but not accurate
they
and accurate nor
compare?
precise precise
Can you define accuracy vs. precision?

Precision and Accuracy
• Measurements can be made with varying degrees of precision.

• It concerns with the fineness of distinctions made between the attributes
that compose a variable.
• Eg. The description of a woman as “43 years old” is more precise than “in
her forties.”
• Precise measurements are superior to imprecise ones
• Exact precision is not always necessary or desirable.
• Don’t confuse precision with accuracy
• Special attention to two technical considerations: Reliability and Validity.
RELIABILITY
• That quality of measurement methods that suggests that the same data
would have been collected each time in repeated observations of the same
phenomenon.
• In the context of a survey, we would expect that the question “Did you
attend religious services last week?” would have higher reliability than the
question “About how many times have you attended religious services in
your life?” This is not to be confused with validity.
RELIABILITY
• Reliability is when a particular technique, applied repeatedly to the Same object,
yields the same result each time.
• E.g. Approximation vs. measuring through scale

• Reliability does not ensure accuracy
• Element of bias
• Reliability problems crop up in many forms.
• Reliability is a concern- as no guard against the observer’s subjectivity.
Test-Retest Method
• Technique to make the same measurement more than once
• If answers vary, the measurement method may NOT be reliable.
• E.g.. Research on health hazard appraisal (HHA) the risks associated with
various background and lifestyle factors, making it possible for physicians to
counsel their patients appropriately.
• An ovary present in the first study was missing in the second study
• One subject was 55 years old in the first study and 50 years old three months later
• Test-retest revealed that this data-collection method was not especially reliable.
• Memory , maturation and change of perspective

Split-Half Method
• It’s good to make more than one measurement of any subtle or complex Social
concept, such as prejudice, alienation, or social class.
• This procedure lays the groundwork for another check on reliability.

• Eg. We have a questionnaire that contains ten items to measure prejudice against
women. Using the split half technique, you would randomly assign those ten items to
two sets of five. Each set should provide a good measure of prejudice against women,
and the two sets should classify respondents the same way.
• If the two sets of items classify people differently, you most likely have a
problem of reliability in your measure of the variable.
USING ESTABLISHED MEASURES
• To ensure reliability in getting information, we can use measures that have
proved their reliability in previous research
• The heavy use of measures, though, does not guarantee their reliability.
• For example, the Scholastic Assessment Tests (SATs) and the Minnesota Multiphasic
Personality Inventory (MMPI) have been accepted as estb. standards in their
respective domains for decades. In recent years, though, they’ve needed fundamental
overhauling to reflect changes in society, eliminating outdated topics and gender bias
in wording.
RELIABILITY OF RESEARCH
WORKERS
• Measurement unreliability may also be generated by research workers,
interviewers and coders. There are ways to check on reliability in such cases.
• Cases with inconsistency can be evaluated more carefully and resolved.
• Clarity, specificity, training, and practice can prevent a great deal of

unreliability and grief.
• Even total reliability, Doesn’t ensure that our measures actually measure, What
we think they measure.
validity
• A term describing a measure that accurately reflects the concept it is
intended to measure.
• Validity means that we are actually measuring what we say we are
measuring.
• A measure of social class should measure social class, not political orientations.
• Your IQ would seem a more valid measure of your intelligence than the number of
hours you spend in the library.
• We may agree to its relative validity on the basis of
• Face validity
• Criterion-related validity
• Construct validity
• Content validity
Validity
• Evidence that a measure assesses the construct

• Reasons for Invalid Measures
• Different understanding of items
• Different use of the scale (Response Styles)
• Intentionally presenting false information (socially desirable
responding, other-deception)
• Unintentionally presenting false information (self-deception)
TYPES OF VALIDITY
CRITERION CONTENT CONSTRUCT

VALIDITY VALIDITY VALIDITY
FACE VALIDITY
• The quality of an indicator/ question/ test that makes it a reasonable
measure of a variable.
• Eg. Church attendance is an indication of religiosity. It has face

validity.
• Eg .Counting the number of grievances filed with the union will

measure morale. The measure is valid “on its face,” whether or not
it’s adequate?
14
criterion-related validity
• The degree to which a measure relates to some external criterion or another

known measure
• Eg., the validity of College Board tests is shown in their ability to predict
the college success of students.
• Also called predictive validity
• Criterion-related (predictive)
• Attitude test to predict performance in a library skills program
• Criterion-related (diagnostic)
• How well does the test diagnose current problems with library use?
Content validity
• Extent to which items on the measure are a good representation of the
construct
• The degree to which a measure covers the range of meanings included

within a concept.
• E.g., Is your job interview based on what is required for the job?
• E.g., A test of mathematical ability cannot be limited to addition but also
needs to cover subtraction, multiplication, division, and so forth.
• E.g. If we’re measuring prejudice, do our measurements reflect all types of
prejudice, including prejudice against racial and ethnic groups, religious
minorities, women, the elderly, and so on?
Construct validity
• Based on the logical relationships among variables
• The degree to which a measure relates to other variables as expected

within a system of theoretical relationships.
• Eg. Marital Satisfaction, and you want to assess its validity.
• Tests of construct validity, then, can offer a weight of evidence that your
measure either does or doesn’t tap the quality you want it to measure,
without providing definitive proof.
17
Tension between Reliability and Validity
• A tension often arises between the criteria of reliability and validity, forcing a
trade-off between the two.
• Two quite different approaches to social research: quantitative, nomothetic,
structured techniques and qualitative, idiographic methods such as field
research and historical studies on the other. The former methods tend to be
more reliable, the latter more valid.
• If no clear agreement on how to measure a concept, measure it several
different ways.
• If the concept has several dimensions, measure them all.
• Measure concepts in ways that help us understand utility and the world
around us.
The Ethics of Measurement
• Measurement decisions can sometimes be judged by ethical standards.
• Most of the concepts of interest to social researchers are open to varied

meanings.
• Conceptualization and Measurement must never be guided by bias and

preferences for particular research outcomes
• E.G., Interested in sampling public opinion on the abortion issue in the

United States. One side of the debate as “pro-choice” or as “pro-abortion.”

Criteria of Measurement Quality

Uploaded by

Copyright:

Available Formats

Criteria of Measurement Quality

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Criteria of Measurement Quality

Uploaded by

Copyright:

Available Formats

CRITERIA OF MEASUREMENT QUALITY

• We learned that there are things , that cant be measured , then we

• Yardsticks against which we judge our relative success or failure in

Can you define accuracy vs. precision?

• Measurements can be made with varying degrees of precision.

• E.g. Approximation vs. measuring through scale

• Technique to make the same measurement more than once

• If answers vary, the measurement method may NOT be reliable.

• Memory , maturation and change of perspective

• This procedure lays the groundwork for another check on reliability.

• Cases with inconsistency can be evaluated more carefully and resolved.

• Clarity, specificity, training, and practice can prevent a great deal of

• Evidence that a measure assesses the construct

CRITERION CONTENT CONSTRUCT

• Eg. Church attendance is an indication of religiosity. It has face

• Eg .Counting the number of grievances filed with the union will

• The degree to which a measure relates to some external criterion or another

• The degree to which a measure covers the range of meanings included

• The degree to which a measure relates to other variables as expected

• Eg. Marital Satisfaction, and you want to assess its validity.

• Measurement decisions can sometimes be judged by ethical standards.

• Most of the concepts of interest to social researchers are open to varied

• Conceptualization and Measurement must never be guided by bias and

• E.G., Interested in sampling public opinion on the abortion issue in the

You might also like