Contents
Week 1........................................................................................................................................................... 2
Lecture 1 .................................................................................................................................................... 2
Lecture 2 .................................................................................................................................................... 3
Chapter 8 ................................................................................................................................................... 7
Chapter 19 ................................................................................................................................................. 9
Chapter 9 ................................................................................................................................................. 16
Week 2......................................................................................................................................................... 18
Lecture 3 .................................................................................................................................................. 18
Chapter 20 ............................................................................................................................................... 22
Video: cluster analysis – the basic idea and step 1-3 .............................................................................. 26
Tutorial 2 ................................................................................................................................................. 28
Week 3......................................................................................................................................................... 29
Lecture 4 .................................................................................................................................................. 29
Week 4......................................................................................................................................................... 34
Lecture 5 .................................................................................................................................................. 34
Lecture 6 .................................................................................................................................................. 42
Chapter 16 ............................................................................................................................................... 46
Chapter 17 ............................................................................................................................................... 51
Tutorial 4 ................................................................................................................................................. 58
Week 5......................................................................................................................................................... 60
Lecture 7 .................................................................................................................................................. 60
Pieters (2017) .......................................................................................................................................... 64
Week 6......................................................................................................................................................... 69
Lecture 8 .................................................................................................................................................. 69
Tutorial 6 ................................................................................................................................................. 74
Week 7......................................................................................................................................................... 75
Lecture 9 .................................................................................................................................................. 75
Chapter 18 ............................................................................................................................................... 78
Tutorial 7 ................................................................................................................................................. 82
1
,Week 1
Lecture 1
The book used in this course is very handy for your master thesis!
Cluster analysis
It is to cluster groups that are kind of the same.
These clusters are made to be able to target people a certain way.
Coming up with a research question often starts with a gap in the literature. You notice that something is
not quite right. Therefore, you need to have read some literature. You use the research of others to build
you research upon. It may help to read in the top 5 journals of marketing, these journals have been
anonymously peer reviewed and revised.
If many other articles refer to a paper, it probably is a good paper.
You write down what is already known about a subject. Based on that you write down hypothesis.
In science you think how things are related, sometimes you don’t find that. The results are insignificant.
That makes you think about it and is therefore not wrong. You just need to start thinking way the
relationship did not exist.
Hour glass model for scientific research
Introduction
- Problem introduction
- Problem statement
- Research question
Literature review > looking what is there already
- Conceptual model
Research method
Analysis and results
Conclusion and discussion
- Scientific implications
- Management implications
- Limitations and further research (validity)
This all leads to new research questions
Research starts with conceptualization.
Conceptualization = drawing boundaries around terms to make them tangible.
‘What is mean with X or Y in this research?’
The goal is to eliminate vagueness and ambiguity.
Based on that you come to a conceptual model.
To be defined in a conceptual model
- Concepts (and dimension)
2
,- Relations
- Next step: operationalization
Operationalization
= To define a concept or variable in such a way that we can measure it quantitatively
How should we measure concept X?
Which empirical observations should be made to measure the existence of a concept?
Measurement level
- Nominal > just a name.
- Ordinal > some order in it, but no fixed intervals between the levels.
- Interval > the jump between the ‘categories’ is the same. Temperature.
- Ratio > there is a natural zero. 10 euro’s is twice as much as 20 euros.
Data preparation
Stage 1: inspection and preparing data for final analysis.
- Clean your dataset.
- Combining items into new dimensions.
Stage 2: final analysis, testing your hypothesis
Lecture 2
Data analysis comes in two stages
3
, Stage 1: inspection and preparing data for final analysis
Missing data – what can you do?
- Listwise deletion > deleting every respondent that has a missing value.
- Pairwise deletion > only delete the respondents of which you do not have data on a certain
(combination) of questions. Sometimes you do not need every variable to be answered for a certain
analysis.
- Replace the missing values. For example, by calculating the average on the data that you have.
The variance won’t be good when you do this.
Weird values – what can you do?
Impossible value? Or an outlier?
Impossible: see missing value.
Outlier:
- How much of an outlier is it?
- What is the effect on analyses?
- What about the use in analyses?
Box plot > can be used to find the outlier.
Stage 2: final analysis, testing your hypotheses
Multi-item scales > 1 latent construct (unmeasured construct), but you need to ask various items to be
able to dive into the complexity of this 1 construct.
Factor analysis
Purpose: reduction of a large quantity of data by finding common variance to
- Retrieve underlying dimensions in your dataset
- Test if the hypothesized dimensions also exist in your dataset.
Common variance = they move parallel to each other. This can be both going up/going down, but it can
also be that one goes up and the other one goes down.
Central questions
- How to reduce a larger set of variables into a smaller set of uncorrelated factors?
- How to interpret these factors (= underlying dimensions) and scores on these factors?
Ultimate goal
Use the dimensions in further analysis
Data
Interval or ratio scaled variables (metric)
4
Week 1........................................................................................................................................................... 2
Lecture 1 .................................................................................................................................................... 2
Lecture 2 .................................................................................................................................................... 3
Chapter 8 ................................................................................................................................................... 7
Chapter 19 ................................................................................................................................................. 9
Chapter 9 ................................................................................................................................................. 16
Week 2......................................................................................................................................................... 18
Lecture 3 .................................................................................................................................................. 18
Chapter 20 ............................................................................................................................................... 22
Video: cluster analysis – the basic idea and step 1-3 .............................................................................. 26
Tutorial 2 ................................................................................................................................................. 28
Week 3......................................................................................................................................................... 29
Lecture 4 .................................................................................................................................................. 29
Week 4......................................................................................................................................................... 34
Lecture 5 .................................................................................................................................................. 34
Lecture 6 .................................................................................................................................................. 42
Chapter 16 ............................................................................................................................................... 46
Chapter 17 ............................................................................................................................................... 51
Tutorial 4 ................................................................................................................................................. 58
Week 5......................................................................................................................................................... 60
Lecture 7 .................................................................................................................................................. 60
Pieters (2017) .......................................................................................................................................... 64
Week 6......................................................................................................................................................... 69
Lecture 8 .................................................................................................................................................. 69
Tutorial 6 ................................................................................................................................................. 74
Week 7......................................................................................................................................................... 75
Lecture 9 .................................................................................................................................................. 75
Chapter 18 ............................................................................................................................................... 78
Tutorial 7 ................................................................................................................................................. 82
1
,Week 1
Lecture 1
The book used in this course is very handy for your master thesis!
Cluster analysis
It is to cluster groups that are kind of the same.
These clusters are made to be able to target people a certain way.
Coming up with a research question often starts with a gap in the literature. You notice that something is
not quite right. Therefore, you need to have read some literature. You use the research of others to build
you research upon. It may help to read in the top 5 journals of marketing, these journals have been
anonymously peer reviewed and revised.
If many other articles refer to a paper, it probably is a good paper.
You write down what is already known about a subject. Based on that you write down hypothesis.
In science you think how things are related, sometimes you don’t find that. The results are insignificant.
That makes you think about it and is therefore not wrong. You just need to start thinking way the
relationship did not exist.
Hour glass model for scientific research
Introduction
- Problem introduction
- Problem statement
- Research question
Literature review > looking what is there already
- Conceptual model
Research method
Analysis and results
Conclusion and discussion
- Scientific implications
- Management implications
- Limitations and further research (validity)
This all leads to new research questions
Research starts with conceptualization.
Conceptualization = drawing boundaries around terms to make them tangible.
‘What is mean with X or Y in this research?’
The goal is to eliminate vagueness and ambiguity.
Based on that you come to a conceptual model.
To be defined in a conceptual model
- Concepts (and dimension)
2
,- Relations
- Next step: operationalization
Operationalization
= To define a concept or variable in such a way that we can measure it quantitatively
How should we measure concept X?
Which empirical observations should be made to measure the existence of a concept?
Measurement level
- Nominal > just a name.
- Ordinal > some order in it, but no fixed intervals between the levels.
- Interval > the jump between the ‘categories’ is the same. Temperature.
- Ratio > there is a natural zero. 10 euro’s is twice as much as 20 euros.
Data preparation
Stage 1: inspection and preparing data for final analysis.
- Clean your dataset.
- Combining items into new dimensions.
Stage 2: final analysis, testing your hypothesis
Lecture 2
Data analysis comes in two stages
3
, Stage 1: inspection and preparing data for final analysis
Missing data – what can you do?
- Listwise deletion > deleting every respondent that has a missing value.
- Pairwise deletion > only delete the respondents of which you do not have data on a certain
(combination) of questions. Sometimes you do not need every variable to be answered for a certain
analysis.
- Replace the missing values. For example, by calculating the average on the data that you have.
The variance won’t be good when you do this.
Weird values – what can you do?
Impossible value? Or an outlier?
Impossible: see missing value.
Outlier:
- How much of an outlier is it?
- What is the effect on analyses?
- What about the use in analyses?
Box plot > can be used to find the outlier.
Stage 2: final analysis, testing your hypotheses
Multi-item scales > 1 latent construct (unmeasured construct), but you need to ask various items to be
able to dive into the complexity of this 1 construct.
Factor analysis
Purpose: reduction of a large quantity of data by finding common variance to
- Retrieve underlying dimensions in your dataset
- Test if the hypothesized dimensions also exist in your dataset.
Common variance = they move parallel to each other. This can be both going up/going down, but it can
also be that one goes up and the other one goes down.
Central questions
- How to reduce a larger set of variables into a smaller set of uncorrelated factors?
- How to interpret these factors (= underlying dimensions) and scores on these factors?
Ultimate goal
Use the dimensions in further analysis
Data
Interval or ratio scaled variables (metric)
4
