Measurement Theory in Marketing Research

1
Measurement Theory in Marketing Research
2
Measurement

• What is measurement?
• Assignment of numerals to objects to represent
  quantities of attributes
• Dont measure the object -- measure attributes of
  the object
• Dont measure a person -- measure their weight,
  height, social class, GPA, etc.
• Definition does not suggest how to measure the
  attributes

3
Measurement

• Fundamentals of Measurement
• Measurement Scales
• Four types
• Nominal -- Number is used for identification
  purposes
• Ordinal -- Number is used to reflect order
• Interval -- Number reflects intervals between
  attributes
• Ratio -- Number has an absolute 0

4
Measurement

• Fundamentals of Measurement
• Measurement Error
• XO XT (ES ER)
• XO Observed score for some construct
• XT True score for some construct
• ES Systematic Error
• ER Random Error
• Objective in research -- XO XT
• Measure is valid
• If XR 0 XO XT ES
• Measure is reliable

5
Measurement

• Fundamentals of Measurement
• Measurement Error
• Reliability -- instrument measures the same
  concept every time it is used (XO XT ES)
• Validity -- instrument measures what it intends
  to measure (XO XT)
• Reliability is a necessary, but not sufficient
  indicator of validity

6
Measurement

• Assessing Reliability (XO XT ES )
• Test-Retest Reliability -- consistent responses
  across time
• Internally consistency-- all aspects of the
  measure work together
• Multiple measures (of the same concept) are
  needed
• Laczniak Yogurt is Good/Bad Favorable/Unfavorabl
  e Positive/Negative
• Coefficient alpha k (mean inter-item
  correlation)/1 (k-1) (mean inter-item
  correlation)
• Here 3 items are used to measure attitude
• Need to calculate correlations between each item
  (3) and then compute the mean
• Unidimensionality all measures work together
• Accomplished via factor analysis

7
Measurement

• Indicators of Validity (XO XT)
• Face validity
• Measure looks like it should
• Best to have others (expert judges determine
  this)
• Discriminant Validity
• Measure does not measure some other concept
• Correlation with measure of other concept is very
  low
• Convergent Validity
• Measure corresponds to other measures of this
  concept
• Correlation with other measures of this concept
  is high

8
Measurement

• Suggested procedure for develop reliable and
  valid marketing measures
• Specify domain of the concept
• Generate exhaustive a sample of items
• Collect data
• Purify Measure
• Assess unidimensionality
• Assess internal consistency

9
Measurement

• Suggested procedure for develop reliable and
  valid marketing measures (Contd)
• Collect Data
• Assess Reliability
• Assess Validity
• Develop Norms
• Over time
• Versus Competition

10
Measurement

• Specify domain of the concept
• Conceptual definition of the concept of interest
• PG wants to measure overall performance of
  Depends
• Overall performance perceptions of quality of
  Depends on key attributes
• Style
• Absorption
• Leakage
• Comfort
• Taping
• Generate exhaustive a sample of items
• Assess performance of 5 attributes on a
  seven-point scale
• 1 poor performance
• 7 excellent performance

11
Measurement

• Specify domain of the concept
• Collect data
• Random sample of 300 adult users of Depends from
  across US
• Purify Measure
• Assess unidimensionality
• Factor Analysis analysis of interdependence
• Identify the underlying structure of a number of
  variables
• Do the 5 items used by PG to measure overall
  product performance load on a single variable?
• RESULTS

12
Measurement

• Specify domain of the concept
• Purify Measure (Contd)
• Assess internal consistency
• Reliability assessment (coefficient alpha)
• What is a good alpha?
• Rules of thumb
• New Measure -- .70
• Existing measure -- .85
• Perform item analysis to determine in alpha will
  improve if item is dropped
• RESULTS

13
Measurement

• Assess Validity
• Does measure correlate with other measures of
  same concept?
• Does it NOT correlate with other measure of same
  concept?
• RESULTS
• Develop Norms
• Over time
• Versus Competition