Вы находитесь на странице: 1из 36

Pampers Develops

A Rash
By Group 7
Introduction
• Pampers conducted market survey to find ways to regain
leadership in market
• Three brands: Pampers, Luvs and Huggies, were asked to be rated
on 9 attributes to determine preference for brand
• To position Pampers effectively against Huggies without
cannibalizing Luvs
Objectives
• To determine the effect of different attributes (count per box,
price, value, unisex, style, absorbency, leakage, comfort/size and
taping) on brand preference
• To identify which attributes of diapers were most important in
influencing purchase preference of customers
Frequency Distribution
• Brand Preference
• Count per Box
• Price
• Value
• Unisex
• Style
• Absorbency
• Leakage
• Comfort/Size
• Taping
Frequency Distribution
BRAND PREFERENCE COUNT PER BOX

119
49
48

43

FREQUENCY
42
41

39
FREQUENCY

38

74

64
28

10
4
1
1 2 3 4 5 6 7
1 2 3 4 5 6 7

PRICE VALUE
110

94
78
88

FREQUENCY

64
FREQUENCY

65

37

23
28

3
1
2
1

1 2 3 4 5 6 7 1 2 3 4 5 6 7
FREQUENCY
FREQUENCY

1
2

1
10

2
32

2
33

3
80

3
66

4
92

4
66
UNISEX

5
68

5
72

ABSORBENCY

6
23
6

31

7
3
7

22
Frequency Distribution

FREQUENCY FREQUENCY

1
1

2 2 10
2

34 27
3
3

78 63
4
4

99 93
STYLE

LEAKAGE

5
5

61 70
6
6

25 27
7
7

1 10
Frequency Distribution
COMFORT/SIZE TAPING

91
84

99

83
FREQUENCY

FREQUENCY
59

62
35

32
25

12
11
4

1
1 2 3 4 5 6 7 1 2 3 4 5 6 7
Observation
Cross Tabulation
2-Variable 3-Variable
• Brand Preference vs Count per • Brand Preference vs Count per Box –
Box controlling for Price
• Brand Preference vs Price • Brand Preference vs Unisex – controlling for
• Brand Preference vs Value Style
• Brand Preference vs Unisex • Brand Preference vs Comfort/Size –
• Brand Preference vs Style controlling for Taping
• Brand Preference vs Absorbency
• Brand Preference vs Leakage
• Brand Preference vs Comfort/Size
• Brand Preference vs Taping
Cross Tab – 2 variables
COUNT PER BOX REDEFINED Total
• With increase in count, BP also LOW MEDIUM HIGH
increases LOW 90.90% 43.20% 8.80% 26.30%
BRAND PREFERENCE REDEFINED MEDIUM 9.10% 47.30% 52.80% 46.70%
HIGH 9.50% 38.30% 27.00%
Total 100.00% 100.00% 100.00% 100.00%

• As price charged increases , BP PRICE REDEFINED Total


LOW MEDIUM HIGH
also increases LOW 87.10% 43.20% 7.70% 26.30%
BRAND PREFERENCE REDEFINED MEDIUM 12.90% 46.60% 52.50% 46.70%
HIGH 10.20% 39.80% 27.00%
Total 100.00% 100.00% 100.00% 100.00%

• As value increases , BP also VALUE REDEFINED Total


LOW MEDIUM HIGH
increases LOW 68.30% 38.50% 11.60% 26.30%
BRAND PREFERENCE REDEFINED MEDIUM 29.30% 47.40% 50.30% 46.70%
HIGH 2.40% 14.10% 38.10% 27.00%
Total 100.00% 100.00% 100.00% 100.00%
Cross Tab – 2 variables
UNISEX REDEFINED Total
• With increase in unisex variable, LOW MEDIUM HIGH
BP also increases LOW 55.00% 24.20% 2.40% 26.30%
BRAND PREFERENCE REDEFINED MEDIUM 39.40% 63.60% 44.00% 46.70%
HIGH 5.50% 12.10% 53.60% 27.00%
Total 100.00% 100.00% 100.00% 100.00%

• As style variable increases , BP STYLE REDEFINED Total


LOW MEDIUM HIGH
also increases LOW 55.00% 21.50% 3.70% 26.30%
BRAND PREFERENCE REDEFINED MEDIUM 40.00% 61.30% 40.20% 46.70%
HIGH 5.00% 17.20% 56.10% 27.00%
Total 100.00% 100.00% 100.00% 100.00%

• As absorbency variable ABSORBENCY REDEFINED Total

increases , BP also increases LOW MEDIUM HIGH


LOW 53.50% 19.60% 26.30%
BRAND PREFERENCE REDEFINED MEDIUM 43.00% 63.00% 35.10% 46.70%
HIGH 3.50% 17.40% 64.90% 27.00%
Total 100.00% 100.00% 100.00% 100.00%
Cross Tab – 2 variables
LEAKAGE REDEFINED Total
• With increase in leakage LOW MEDIUM HIGH
variable, BP also increases LOW 54.40% 17.20% 26.30%
BRAND PREFERENCE REDEFINED MEDIUM 42.10% 64.60% 32.20% 46.70%
HIGH 3.50% 18.20% 67.80% 27.00%
Total 100.00% 100.00% 100.00% 100.00%

• As comfort variable increases , COMFORT/SIZE REDEFINED Total

BP also increases LOW MEDIUM HIGH


LOW 52.00% 13.20% 3.50% 26.30%
BRAND PREFERENCE REDEFINED MEDIUM 42.30% 61.50% 37.20% 46.70%
HIGH 5.70% 25.30% 59.30% 27.00%
Total 100.00% 100.00% 100.00% 100.00%

• As taping variable increases , BP TAPING REDEFINED Total


also increases LOW MEDIUM HIGH
LOW 39.00% 14.50% 26.30%
BRAND PREFERENCE REDEFINED MEDIUM 45.90% 51.80% 40.00% 46.70%
HIGH 15.10% 33.70% 60.00% 27.00%
Total 100.00% 100.00% 100.00% 100.00%
Observation
• In 2-variable cross tab, all dependent variable have statistically
significant and positive association with brand preferences.
Cross Tab – 3 variables
PRICE REDEFINED COUNT PER BOX REDEFINED Total
LOW MEDIUM HIGH
LOW BRAND PREFERENCE LOW 88.00% 83.30% 87.10%
REDEFINED MEDIUM 12.00% 16.70% 12.90%
Total 100.00% 100.00% 100.00%
MEDIUM LOW 100.00% 40.30% 27.80% 43.20%
BRAND PREFERENCE
MEDIUM 50.00% 55.60% 46.60%
REDEFINED
HIGH 9.70% 16.70% 10.20%
Total 100.00% 100.00% 100.00% 100.00%
HIGH LOW 33.30% 6.90% 7.70%
BRAND PREFERENCE
MEDIUM 50.00% 52.60% 52.50%
REDEFINED
HIGH 16.70% 40.60% 39.80%
Total 100.00% 100.00% 100.00%
Total LOW 90.90% 43.20% 8.80% 26.30%
BRAND PREFERENCE
MEDIUM 9.10% 47.30% 52.80% 46.70%
REDEFINED
HIGH 9.50% 38.30% 27.00%
Total 100.00% 100.00% 100.00% 100.00%

• With Low price there is no significant difference between medium and low
count per box
Cross Tab – 3 variables
STYLE REDEFINED UNISEX REDEFINED Total
LOW MEDIUM HIGH
LOW LOW 60.50% 21.40% 55.00%
BRAND PREFERENCE
MEDIUM 33.70% 78.60% 40.00%
REDEFINED
HIGH 5.80% 5.00%
Total 100.00% 100.00% 100.00%
MEDIUM LOW 34.80% 27.90% 21.50%
BRAND PREFERENCE
REDEFINED MEDIUM 60.90% 60.50% 63.00% 61.30%
HIGH 4.30% 11.60% 37.00% 17.20%
Total 100.00% 100.00% 100.00% 100.00%
HIGH LOW 11.10% 3.10% 3.70%
BRAND PREFERENCE
MEDIUM 55.60% 38.80% 40.20%
REDEFINED
HIGH 33.30% 58.20% 56.10%
Total 100.00% 100.00% 100.00%
Total LOW 55.00% 24.20% 2.40% 26.30%
BRAND PREFERENCE
MEDIUM 39.40% 63.60% 44.00% 46.70%
REDEFINED
HIGH 5.50% 12.10% 53.60% 27.00%
Total 100.00% 100.00% 100.00% 100.00%

• With medium style and medium brand preference there is insignificant


difference between low medium and high
Cross Tab – 3 variables
TAPING REDEFINED COMFORT/SIZE REDEFINED Total
LOW MEDIUM HIGH
LOW LOW 53.80% 14.60% 16.70% 39.00%
BRAND PREFERENCE
MEDIUM 39.60% 66.70% 27.80% 45.90%
REDEFINED
HIGH 6.60% 18.80% 55.60% 15.10%
Total 100.00% 100.00% 100.00% 100.00%
MEDIUM LOW 41.20% 13.90% 14.50%
BRAND PREFERENCE
REDEFINED MEDIUM 58.80% 55.60% 43.30% 51.80%
HIGH 30.60% 56.70% 33.70%
Total 100.00% 100.00% 100.00% 100.00%
HIGH BRAND PREFERENCE MEDIUM 57.10% 36.80% 40.00%
REDEFINED HIGH 42.90% 63.20% 60.00%
Total 100.00% 100.00% 100.00%
Total LOW 52.00% 13.20% 3.50% 26.30%
BRAND PREFERENCE
MEDIUM 42.30% 61.50% 37.20% 46.70%
REDEFINED
HIGH 5.70% 25.30% 59.30% 27.00%
Total 100.00% 100.00% 100.00% 100.00%

• Brand preference and taping is high with high comfort/size


Regression
Dependent Variable Independent Variable
• Brand Preference • Count per Box
• Price
• Value
• Unisex
• Style
• Absorbency
• Leakage
• Comfort/Size
• Taping
Regression

• The Value of the R square is 0.730

• This means that 73 percent of the


variations in the brand
preference are explained by all
the variables (Taping, Value,
Style, Absorbency, Count Per Box,
Comfort/Size, Price, Unisex,
Leakage)

• From the ANOVA Table, it can


observed that R Square is
significant
Regression
Regression Equation
BP = -3.458 + 0.504X1 + 0.109X2 + 0.016X3 + 0.472X4 – 0.065X5 + 0.0341X6 + 0.253X7 +0.106X8 + 0.020X9

• Only Style is negatively correlated


• Count Per Box, Unisex, Absorbency
are significant
• Price, Value, Style, Leakage,
Comfort and Taping are
insignificant
One-Way ANOVA
Dependent Variable Independent Variable
• Brand Preference • Count per Box
• Price
• Value
H0 : Average score of each group is same • Unisex
• Style
• Absorbency
H1 : Average score of at least two groups is
• Leakage
not same
• Comfort/Size
• Taping
One-Way Anova [ BP vs Count ]
Sum of Squares df Mean Square F Sig.
Between Groups 434.898 2 217.449 90.075 0
Within Groups 716.982 297 2.414
Count Per Box
Significant
Total 1151.88 299

• Result is significant, hence null is


rejected

• At least two means are unequal

• From Tukey analysis we can say that


low category has lowest mean and
high category has highest mean

• Or BP is directly proportion to Count


per Box
One-Way Anova [ BP vs Price ]
Sum of Squares df Mean Square F Sig.

Between Groups 403.532 2 201.766 80.076 0


Within Groups 748.348 297 2.52
Count Per Box Significant
Total 1151.88 299

• Result is significant, hence null is


rejected
• At least two means are unequal
• From Tukey analysis we can say
that low category has lowest mean
and high category has highest
mean
• Or BP is directly proportion to Price
One-Way Anova [ BP vs Value ]
Sum of Squares df Mean Square F Sig.

Between Groups 280.331 2 140.165 47.764 0


Within Groups 871.549 297 2.935
Count Per Box Significant
Total 1151.88 299

• Result is significant, hence null is


rejected
• At least two means are unequal
• From Tukey analysis we can say
that low category has lowest mean
and high category has highest
mean
• Or BP is directly proportion to Value
One-Way Anova [ BP vs Unisex ]
Sum of Squares df Mean Square F Sig.

Between Groups 508.133 2 254.067 117.217 0


Within Groups 643.747 297 2.167
Count Per Box Significant
Total 1151.88 299

• Result is significant, hence null is


rejected

• At least two means are unequal

• From Tukey analysis we can say that


low category has lowest mean and
high category has highest mean

• Or BP is directly proportion to Unisex


Score
One-Way Anova [ BP vs Style]
Sum of Squares df Mean Square F Sig.

Between Groups 434.835 2 217.417 90.054 0


Within Groups 717.045 297 2.414
Count Per Box Significant
Total 1151.88 299

• Result is significant, hence null is


rejected

• At least two means are unequal

• From Tukey analysis we can say that


low category has lowest mean and
high category has highest mean

• Or BP is directly proportion to Style


score
One-Way Anova [ BP vs Absorbency]
Sum of Squares df Mean Square F Sig.

Between Groups 530.346 2 265.173 126.713 0


Within Groups 621.534 297 2.093
Count Per Box Significant
Total 1151.88 299

• Result is significant, hence null is


rejected

• At least two means are unequal

• From Tukey analysis we can say that


low category has lowest mean and
high category has highest mean

• Or BP is directly proportion to
Absorbency
One-Way Anova [ BP vs Leakage]
Sum of Squares df Mean Square F Sig.

Between Groups 528.012 2 264.006 125.683 0


Within Groups 623.868 297 2.101
Count Per Box Significant
Total 1151.88 299

• Result is significant, hence null is


rejected

• At least two means are unequal

• From Tukey analysis we can say that


low category has lowest mean and
high category has highest mean

• Or BP is directly proportion to
Leakage score
One-Way Anova [ BP vs Comfort/Size]
Sum of Squares df Mean Square F Sig.

Between Groups 373.519 2 186.759 71.262 0


Within Groups 778.361 297 2.621
Count Per Box Significant
Total 1151.88 299

• Result is significant, hence null is


rejected

• At least two means are unequal

• From Tukey analysis we can say that


low category has lowest mean and
high category has highest mean

• Or BP is directly proportion to
Comfort
One-Way Anova [ BP vs Taping]
Sum of Squares df Mean Square F Sig.

Between Groups 195.943 2 97.972 30.439 0


Within Groups 955.937 297 3.219
Count Per Box Significant
Total 1151.88 299

• Result is significant, hence null is


rejected

• At least two means are unequal

• From Tukey analysis we can say that


low category has lowest mean and
high category has highest mean

• Or BP is directly proportion to Taping


score
Factor Analysis
Dependent Variable Independent Variable
• Brand Preference • Count per Box
• Price
• Value
• Unisex
• Style
• Absorbency
• Leakage
• Comfort/Size
• Taping
Factor Analysis
Conditions to apply factor analysis:

• Metric Data

• Standardized responses (same


scale)

• Size: 300 > 5*9 (variables)

• Barttlet test of sphericity (significant)

• KMO: Value is greater than 0.5

• Factors obtained from factor analysis


can explain 94.4% and 94.3%
variance in Unisex and Style variables
respectively.
Factor Analysis

• Factors with eigen value >1 are selected.


• Three factors combined together explain 83.959% of variance in the entire data
set
• Percentage of variance explained by factor 1,2 and 3 after rotation are 34%,
28.26% and 21.64% respectively
Factor Analysis
• In rotated component matrix, 0.75 is chosen as cut-off value for factor
loading

• Factor 1 comprises of X6, X7, X8 and X9 which can be named as BASIC


FUNCTIONALITY

• Factor 2 comprises of X1, X2 and X3 and can be named as VALUE FOR


MONEY

• Factor 3 comprises of X4 and X5 and can be named as ADD-ON


FEATURES

• These 3 factors will be independent of each other and correlation will


be 0

• Component Score Coefficient Matrix is


used to calculate factor scores

• Factor scores are standardized scores and


can be used for regression analysis
Factor Analysis
• Linear Regression is applied on zscores

• Zscore of Brand Preference is selected as dependent variable

• Zscores of Factor 1, Factor 2 and Factor 3 are selected as


independent variables

• The regression analysis indicates that 70.6% variation in Brand


Preference can be explained by 3 factors

• All the factors are significantly contributing in


explaining the variance in Brand preference

• BP(Expected) = 4.02+ 1.019*F1+ 0.913*F2+ 0.922*F3

• Factor 1 is the most important in explaining Brand


Preference followed by Factor 3 and Factor 2
Recommendation
Thank You

Вам также может понравиться