[Jaar]
CMA lectures
MASTER MARKETING 2021-2022
VRIJE UNIVERSITEIT.
,Table of content
Lecture 3: Measurement and scaling: reliability, validity and dimensionality ................................................ 2
Measurement and marketing ............................................................................................................................... 2
Different types of scales in marketing .................................................................................................................. 2
Multiple item measurement theory...................................................................................................................... 3
Scale evaluation: reliability & validity .................................................................................................................. 3
Factor analysis ...................................................................................................................................................... 5
Lecture 4: Creating perceptual maps: using factor analysis ......................................................................... 10
Lecture 7 .................................................................................................................................................. 17
Introduction to database marketing and data mining ....................................................................................... 37
Predicting Customer Response and RFM Approach ........................................................................................... 40
Lecture 8: Logistic regression .................................................................................................................... 43
Lecture 9 Understanding Individual Customer ........................................................................................... 47
Lecture 10 ................................................................................................................................................ 50
Lecture 11: wrapping up ........................................................................................................................... 61
Lecture 3: Measurement and Scaling: Reliability, Validity, Dimensionality ....................................................... 62
Assessing Dimensionality of Constructs using Factor Analysis ...................................................................... 63
Lecture 4 Creating Perceptual Maps: Using Factor Analysis ........................................................................ 67
Lecture 5 Market Response Models........................................................................................................... 70
Lecture 6 Mediation and Moderation ........................................................................................................ 72
Lectures 7 & 8: Predicting Customer Response using Logistic Regression..................................................... 74
Lecture 9 & 10: conjoint analysis ............................................................................................................... 76
,Lecture 3: Measurement and scaling: reliability, validity and dimensionality
Contents:
▪ Measurement and marketing
▪ Different types of scales in marketing
- Comparative scales
- Non-comparative scales
▪ Multiple item measurement theory
▪ Scale evaluation
- Reliability
- Validity
▪ Factor analysis and dimensionality of constructs (scale analysis)
Measurement and marketing
Testing theories in order to measure (unobserved) latent constructs
- Tendency to give a social desirable answer
- Materialism
- Susceptibility to social comparisons
- Involvement
- Need for uniqueness
- Customer loyalty
- Impulsive buying tendency
- Price sensitivity
- Attitude
- Satisfaction
Definitions
- Measurement: assigning numbers to characteristics (attributes) of object or people according
to a pre-specified rule.
- Scaling: generation of a continuum upon which measured objects are located
o Example: attitude towards a brand: Unfavorable, neutral, favorable.
Measurement scales:
- Nominal
- Ordinal
- Interval: No true zero point
- Ratio
Why is it important?
- Identification of the measurement scale depends on the basic nature of the attribute
- Higher levels of measurement allow more in-depth statistical analyses
- Critical in determining which data analysis techniques are the most applicable to the data.
o Chi square → Nominal
o Pearsons correlation coefficient → interval & ratio
o Linear regression → DV Is interval & ratio
o Logistics regression → DV is nominal.
Different types of scales in marketing
Most popular scaling techniques
Comparative scaling techniques
1. Paired comparison scaling
2. Rank order scaling
3. Constant sum scale
non-comparative scaling techniques
1. Likert scale
2. Semantic differential
Comparative scaling
- Paired comparison scaling: respondent needs to select one object (out of 2) according to some
criterion.
, o Heineken or Grolsch
o Heineken or Bavaria
- Rank order: respondents need to order several objects according to some criterion.
o 1. Grolsch, 2 Heineken, 3 Bavaria.
- Constant sum scaling
Respondents allocate a fixed amount of points among several objects according to some criterion.
o Grosch 50, Heineken 30, Bavaria 20.
Non-comparative scaling
Each stimulus object is scaled independently of the other object.
- Likert scale: respondents need to indicate the degree of agreement to a series of statements.
o Pepsi is a sweet drink:
Totally disagree 1 2 3 4 5 Totally agree
- Semantic differential scale: Rating scale with endpoints associated with the bipolar labels
o Pepsi is: sweet __:__:__:__:__:__:__ sour
- The number of scale categories: 5 to 9, depends on the respondents knowledge and involvement.
- Odd vs. even number of categories: neutral response allowed or not
- Nature and degree of verbal descriptions
o Words, numbers pictures or label all vs. only extremes.
Multiple item measurement theory
- Why do personality quizzes, exams and intelligence test consist of several questions?
- Why do we often use multi-item (question) scales instead of single-item scales
o To minimize error → Reliability
o To capture the complex / heterogeneous nature of the construct / characteristic →Validity
- Sometimes single-item scales are sufficient
o Objective, concrete constructs (age, income, purchase intention)
Multiple item measurement
X o = X t + Xs + Xe
Xo = observed score (e.g., your IBT-score)
Xt = true score (e.g., your real impulsive buying tendency)
Xs = systematic error (non-random error) (e.g., social desirability bias)
Xe = random error (e.g., being distracted for a moment, mood)
Scale evaluation: reliability & validity
Reliability: is it stable? The extent to which the measurement instrument gives the same results when
the measurement is repeated.
CMA lectures
MASTER MARKETING 2021-2022
VRIJE UNIVERSITEIT.
,Table of content
Lecture 3: Measurement and scaling: reliability, validity and dimensionality ................................................ 2
Measurement and marketing ............................................................................................................................... 2
Different types of scales in marketing .................................................................................................................. 2
Multiple item measurement theory...................................................................................................................... 3
Scale evaluation: reliability & validity .................................................................................................................. 3
Factor analysis ...................................................................................................................................................... 5
Lecture 4: Creating perceptual maps: using factor analysis ......................................................................... 10
Lecture 7 .................................................................................................................................................. 17
Introduction to database marketing and data mining ....................................................................................... 37
Predicting Customer Response and RFM Approach ........................................................................................... 40
Lecture 8: Logistic regression .................................................................................................................... 43
Lecture 9 Understanding Individual Customer ........................................................................................... 47
Lecture 10 ................................................................................................................................................ 50
Lecture 11: wrapping up ........................................................................................................................... 61
Lecture 3: Measurement and Scaling: Reliability, Validity, Dimensionality ....................................................... 62
Assessing Dimensionality of Constructs using Factor Analysis ...................................................................... 63
Lecture 4 Creating Perceptual Maps: Using Factor Analysis ........................................................................ 67
Lecture 5 Market Response Models........................................................................................................... 70
Lecture 6 Mediation and Moderation ........................................................................................................ 72
Lectures 7 & 8: Predicting Customer Response using Logistic Regression..................................................... 74
Lecture 9 & 10: conjoint analysis ............................................................................................................... 76
,Lecture 3: Measurement and scaling: reliability, validity and dimensionality
Contents:
▪ Measurement and marketing
▪ Different types of scales in marketing
- Comparative scales
- Non-comparative scales
▪ Multiple item measurement theory
▪ Scale evaluation
- Reliability
- Validity
▪ Factor analysis and dimensionality of constructs (scale analysis)
Measurement and marketing
Testing theories in order to measure (unobserved) latent constructs
- Tendency to give a social desirable answer
- Materialism
- Susceptibility to social comparisons
- Involvement
- Need for uniqueness
- Customer loyalty
- Impulsive buying tendency
- Price sensitivity
- Attitude
- Satisfaction
Definitions
- Measurement: assigning numbers to characteristics (attributes) of object or people according
to a pre-specified rule.
- Scaling: generation of a continuum upon which measured objects are located
o Example: attitude towards a brand: Unfavorable, neutral, favorable.
Measurement scales:
- Nominal
- Ordinal
- Interval: No true zero point
- Ratio
Why is it important?
- Identification of the measurement scale depends on the basic nature of the attribute
- Higher levels of measurement allow more in-depth statistical analyses
- Critical in determining which data analysis techniques are the most applicable to the data.
o Chi square → Nominal
o Pearsons correlation coefficient → interval & ratio
o Linear regression → DV Is interval & ratio
o Logistics regression → DV is nominal.
Different types of scales in marketing
Most popular scaling techniques
Comparative scaling techniques
1. Paired comparison scaling
2. Rank order scaling
3. Constant sum scale
non-comparative scaling techniques
1. Likert scale
2. Semantic differential
Comparative scaling
- Paired comparison scaling: respondent needs to select one object (out of 2) according to some
criterion.
, o Heineken or Grolsch
o Heineken or Bavaria
- Rank order: respondents need to order several objects according to some criterion.
o 1. Grolsch, 2 Heineken, 3 Bavaria.
- Constant sum scaling
Respondents allocate a fixed amount of points among several objects according to some criterion.
o Grosch 50, Heineken 30, Bavaria 20.
Non-comparative scaling
Each stimulus object is scaled independently of the other object.
- Likert scale: respondents need to indicate the degree of agreement to a series of statements.
o Pepsi is a sweet drink:
Totally disagree 1 2 3 4 5 Totally agree
- Semantic differential scale: Rating scale with endpoints associated with the bipolar labels
o Pepsi is: sweet __:__:__:__:__:__:__ sour
- The number of scale categories: 5 to 9, depends on the respondents knowledge and involvement.
- Odd vs. even number of categories: neutral response allowed or not
- Nature and degree of verbal descriptions
o Words, numbers pictures or label all vs. only extremes.
Multiple item measurement theory
- Why do personality quizzes, exams and intelligence test consist of several questions?
- Why do we often use multi-item (question) scales instead of single-item scales
o To minimize error → Reliability
o To capture the complex / heterogeneous nature of the construct / characteristic →Validity
- Sometimes single-item scales are sufficient
o Objective, concrete constructs (age, income, purchase intention)
Multiple item measurement
X o = X t + Xs + Xe
Xo = observed score (e.g., your IBT-score)
Xt = true score (e.g., your real impulsive buying tendency)
Xs = systematic error (non-random error) (e.g., social desirability bias)
Xe = random error (e.g., being distracted for a moment, mood)
Scale evaluation: reliability & validity
Reliability: is it stable? The extent to which the measurement instrument gives the same results when
the measurement is repeated.
