Exam Marketing Research Methods
Thursday, November 5 2015
TEACHER
The exam contains XX pages.
The exam consists of 4 parts with several sub-questions.
Please answer each question in the corresponding answer box.
You have 3 hours to complete the exam (14.00-17.00 hrs).
Make sure that you write your name and student number the first page!
Please answer in English (Dutch is not allowed by the faculty).
The grades for the exam will be published on Nestor.
We wish you lots of success!!!
Maximum number of credits per question:
Part 1: Regression, Third variables & Binary data 29 credits
Part 2: Conjoint analysis 26 credits
Part 3: Factor analysis & Reliability analysis 30 credits
Part 4: Cluster analysis 15 credits
1
, Part 1. AN(C)OVA, Regression, and Third variables (28 credits)
The high-tech Li-Po battery manufacturer HyperLiPo wants to see how the capacity of their manufactured
batteries affects the sales of electric cars in several countries.
1. As a first step, they want to find out whether people want to spend more on cars, when introducing a
new, higher-capacity, battery. To do so, they look at the average money spent on three different types
of cars, gas-only, pure-electrical and hybrid cars, before and after introducing the new batteries. The
table below summarizes the average spending across all countries.
Before (in $K) After (in $K) Mean
Gas 25 22 23,5
Pure-electrical 32 32,5 32,25
Hybrid 29 35 32
Mean 28,667 29,83 29,25
24,67 95,17 49,625
Source Variation (sum of Degree of freedom Variance (mean
squares SS) square)
BetweenSS 2,04 1 2,04 F = 0,07
WithinSS 119,84 4 29,96
TotalSS 121,88 5 24,38 (F critical =6,61)
a. Given the tables above, did the introduction of the new battery had an effect on willingness
to pay for the cars? Explain. (3 credits)
Since the within variance (variance between the car types during each period) is not much different than
the total variance, i.e. there not much difference caused by introduction of the new batty type, we can see
that introducing the new battery does not change the willingness to pay for the cars. It changes the way
people would have been paying for each type of car, but do not change the overall willingness to pay for
the cars
b. You find out that the yearly average income in the countries affects willingness to pay. Since
the company wants to export its products to a wide array of countries, ranging from Finland to
Brazil, the marketing department of the company suggests to account for these contrasts in
income when trying to explain the willingness to pay. How would you account for this variable
in the ANOVA analysis on the previous page? Also, explain what is the advantage of
incorporating income in this way. (3 credits)
Here we can add income as a covariate, which turns the method to ANCOVA. In this way we can control for
different income levels in different countries, and hence we will have a better test for difference in sales. It
is important to also incorporate homogeneity of slopes, since adding income should not have changed
before and after introducing the new battery type. This can be done by adding the interaction of factorial
variable (battery type) and income, and testing for significance of the effect.
2
Thursday, November 5 2015
TEACHER
The exam contains XX pages.
The exam consists of 4 parts with several sub-questions.
Please answer each question in the corresponding answer box.
You have 3 hours to complete the exam (14.00-17.00 hrs).
Make sure that you write your name and student number the first page!
Please answer in English (Dutch is not allowed by the faculty).
The grades for the exam will be published on Nestor.
We wish you lots of success!!!
Maximum number of credits per question:
Part 1: Regression, Third variables & Binary data 29 credits
Part 2: Conjoint analysis 26 credits
Part 3: Factor analysis & Reliability analysis 30 credits
Part 4: Cluster analysis 15 credits
1
, Part 1. AN(C)OVA, Regression, and Third variables (28 credits)
The high-tech Li-Po battery manufacturer HyperLiPo wants to see how the capacity of their manufactured
batteries affects the sales of electric cars in several countries.
1. As a first step, they want to find out whether people want to spend more on cars, when introducing a
new, higher-capacity, battery. To do so, they look at the average money spent on three different types
of cars, gas-only, pure-electrical and hybrid cars, before and after introducing the new batteries. The
table below summarizes the average spending across all countries.
Before (in $K) After (in $K) Mean
Gas 25 22 23,5
Pure-electrical 32 32,5 32,25
Hybrid 29 35 32
Mean 28,667 29,83 29,25
24,67 95,17 49,625
Source Variation (sum of Degree of freedom Variance (mean
squares SS) square)
BetweenSS 2,04 1 2,04 F = 0,07
WithinSS 119,84 4 29,96
TotalSS 121,88 5 24,38 (F critical =6,61)
a. Given the tables above, did the introduction of the new battery had an effect on willingness
to pay for the cars? Explain. (3 credits)
Since the within variance (variance between the car types during each period) is not much different than
the total variance, i.e. there not much difference caused by introduction of the new batty type, we can see
that introducing the new battery does not change the willingness to pay for the cars. It changes the way
people would have been paying for each type of car, but do not change the overall willingness to pay for
the cars
b. You find out that the yearly average income in the countries affects willingness to pay. Since
the company wants to export its products to a wide array of countries, ranging from Finland to
Brazil, the marketing department of the company suggests to account for these contrasts in
income when trying to explain the willingness to pay. How would you account for this variable
in the ANOVA analysis on the previous page? Also, explain what is the advantage of
incorporating income in this way. (3 credits)
Here we can add income as a covariate, which turns the method to ANCOVA. In this way we can control for
different income levels in different countries, and hence we will have a better test for difference in sales. It
is important to also incorporate homogeneity of slopes, since adding income should not have changed
before and after introducing the new battery type. This can be done by adding the interaction of factorial
variable (battery type) and income, and testing for significance of the effect.
2
