Transcript Statistics for Marketing and Consumer Research

Data preparation and
descriptive statistics
Chapter 4
Statistics for Marketing & Consumer Research
Copyright © 2008 - Mario Mazzocchi
1
Data editing
•
•
•
•
•
•
•
•
Are non-response errors within acceptable limits?
Does the questionnaire meet the basic
respondent requirements?
Are the response in the questionnaire complete?
Are they consistent and clear?
Should low quality questionnaires be replaced or
discarded?
How should the database be organized?
How are the questions coded?
How is the transcribing process organized?
Statistics for Marketing & Consumer Research
Copyright © 2008 - Mario Mazzocchi
2
Non-response errors and
countermeasures
• Refusals
• contacts prior to the interview
• incentives
• follow-ups
• Not-at-homes
• Call-back plan
• Other countermeasures
• Interview a sub-sample of non-respondents (with a different
interview method)
• Substitute non-respondents with other respondents (from the same
sampling frame), that are similar to the non-respondents with
respect to some key characteristics.
• Post-editing (discussed later)
Statistics for Marketing & Consumer Research
Copyright © 2008 - Mario Mazzocchi
3
Problems in returned
questionnaires
• Basic requirements
• Has it reached the targeted respondent (or did someone else
respond).
• Filter questions ensure that the respondent is qualified to answer
• Invalid/deceptive questionnaire should be discarded
• Completeness of questionnaires
• Missing response to some items (e.g. sensitive questions, lack of
pages)
• Consistency
• Specific structures and multiple related questions allow a quality
check (inconsistencies, ambiguities, etc.)
• E.g. How much do you drive? Do you have a driving license?
Statistics for Marketing & Consumer Research
Copyright © 2008 - Mario Mazzocchi
4
Dealing with unsatisfactory
responses
• Best solution: go back to the respondent and clarify the issues (with a
different interview method)
• Call-backs are expensive, but improve quality
• Alternative solution: assign missing values to unsatisfactory responses
• If there is a large proportion of missing values, better to discard the whole
questionnaire
• If there is a small proportion of incomplete questionnaires, better to
discard the whole questionnaire
• The discarding procedure
• may reintroduce biases that the sampling procedure was expected to avoid
• Example: all low quality questionnaires come from the same socio-economic
group; discarding them reduces the representativeness of the sample
• Non-random unsatisfactory responses indicates a problem in the survey
procedure
• Other statistical procedures deal with missing data (discussed later)
Statistics for Marketing & Consumer Research
Copyright © 2008 - Mario Mazzocchi
5
From the questionnaire to the data
sheet
1)
Organize the data base
•
•
2)
Clearly define the structure of the electronic records and the
number of variables
Example: a multiple-choice item can be classified as a single
categorical variable or as a set of binary variables
Prepare the codebook
•
•
•
•
Assign variable names
Decide the variable types (see lecture 1 – qualitative vs.
quantitative, nominal vs. ordinal, etc.)
Decide the variable width (decimals, etc.)
Decide the coding for the identifications of missing values
(e.g. -999 non-response, -888 unreadable, etc.)
Statistics for Marketing & Consumer Research
Copyright © 2008 - Mario Mazzocchi
6
Codebook example
Data set
0000000001111111111222222222233333333
1234567890123456789012345678901234567
1James
37abae4231831London
42
2Lucy
24bcbd3021233Oxford
32
3Daniel
28ddad177-999Brighton
10
Codebook
Position
Variable
Description (Question)
Coding
Col 1
Col 2-10
Col 11-12
CODE
NAME
AGE
Respondent code
Respondent name (Q1)
Respondent age (Q2)
Col 13
JOB
Employment(Q8)
Col 14
EDUC
Education level (Q9)
Quantitative
String
Quantitative
-8=non response
-9=refusal
Qual. Nominal
a=employed
b=unemployed
c=retired
d=other
8=non response
9=refusal
Qual. Ordinal
a=no formal ed.
b=primary sc.
c=secondary sc.
d=University dg.
8=non response
9=refusal
Statistics for Marketing & Consumer Research
Copyright © 2008 - Mario Mazzocchi
7
The transcription process
• With computer-assisted administration methods (CAPI,
CATI or CAWI), the interviewer keys in the answers directly
and the software automatically produces the data-set
• The software also performs consistency checks to validate
the data-set and anomalies are signalled to the interviewer
• For other questionnaires, there is an option for electronic
reading using appropriate optical scanners and software
• In some circumstances, however, the questionnaires are
keyed into the compute; this is a potential source of error;
random checks on the entered data are advisable.
Statistics for Marketing & Consumer Research
Copyright © 2008 - Mario Mazzocchi
8
Post-editing treatment
• The editing step creates the data-set
• The post-editing process is a series of operations to
improve the quality of the data prior to the actual
statistical analysis through:
•
•
•
•
•
Further consistency checks
Missing data treatment
Weighting cases
Transforming variables
Creating new variables
Statistics for Marketing & Consumer Research
Copyright © 2008 - Mario Mazzocchi
9
Post-editing consistency checks
• More complex automatic checks than those in the editing
step
• Check for outliers
• Test whether some of the recorded quantitative values are too high
or too low
• Check whether multiple choice responses are out of the established
range
• Set rules (usually by software) for consistency checks:
• Example: an automatic search for those who declare they drive but
have no driving license
• Cross-collected data with that from an external source
(mainly census and other demographic data) to detect
anomalies.
Statistics for Marketing & Consumer Research
Copyright © 2008 - Mario Mazzocchi
10
Missing data treatment
• Problems with missing data
• Reduction in sample size (hence precision of estimates)
• Introduction of systematic biases when missing data are related to
specific characteristics (e.g. missing data in the lower income
range)
• When missing data are not a problem:
• Large sample size
• Non-response (missing data) are random, as they do not depend on
respondent characteristics (missing at random or MAR data)
• They can be discarded
• Casewise or listwise deletion – all data for the case with missing
data are deleted
• Pairwise deletion – for each estimation all valid cases are
considered, the same case might enter in one estimation and not
in another because of missing data
Statistics for Marketing & Consumer Research
Copyright © 2008 - Mario Mazzocchi
11
Non-random missing data
• Diagnosis: test where data are MAR
• Divide the sample into two group (missing data vs. non-missing
data)
• Perform mean comparison tests on relevant respondent
characteristics (control variables)
• Cures:
• Statistical imputation: missing information replaced by information
already in the sample
• Mean substitution (reduces data variability)
• Regression analysis (see lecture 9) using relations with other
variables
• Multiple imputation: several imputation methods are exploited
and an average of the estimates is used
• EM algorithm: assumes a specific distribution (usually normal),
then obtain estimates through maximum likelihood – the
procedure is iterative
• Directly into statistical analysis: for example, treating cases with
missing values as a stand – alone group
Statistics for Marketing & Consumer Research
Copyright © 2008 - Mario Mazzocchi
12
Weighting cases
• If some particular sub-group of the population might be
under- or over-represented in the sample, applying a
weight to each case restores the representativeness of the
sample.
• When to apply weights:
• with stratified sampling or cluster sampling, weights are necessary
and depend on the sampling design (see lecture 5)
• Probabilistic samples are expected to be self-weighted, but the selfweighting property is undermined by non-responses: weights adjust
the sample
• Weighting can also be useful to value the information of a sub-group
of the population compared to others, with an explicit choice of the
researcher in relation to the final objective
Statistics for Marketing & Consumer Research
Copyright © 2008 - Mario Mazzocchi
13
Transforming and creating variables
Variables can be modified (or new variables can be
generated) through:
(a) Mathematical transformations
•
E.g. logarithmic transformation to reduce variability
(b) Banding
•
Categorization of quantitative variables
(c) Recoding
•
Change the response categories of a qualitative variable
(d) Ranking
•
Transform a scale value into an ordinal variable which reflects
ranking (e.g. transformation into quartiles)
Statistics for Marketing & Consumer Research
Copyright © 2008 - Mario Mazzocchi
14
Post-editing in SPSS
• Check for consistency by screening variables
Statistics for Marketing & Consumer Research
Copyright © 2008 - Mario Mazzocchi
15
Missing data and SPSS (1)
• Mean/ median interpolation replacement based on
the target variable only
Statistics for Marketing & Consumer Research
Copyright © 2008 - Mario Mazzocchi
16
Missing data & SPSS (2)
• More complex imputation techniques
Statistics for Marketing & Consumer Research
Copyright © 2008 - Mario Mazzocchi
17
Weighting cases in SPSS
Statistics for Marketing & Consumer Research
Copyright © 2008 - Mario Mazzocchi
18
Transforming and creating variables in
SPSS
• COMPUTE: performs mathematical
computations and transformations
(with If condition)
• RECODE: allows to re-classify a
nominal or ordinal variable into a
smaller or larger set of categories.
• VISUAL BANDER: categorizes a scale
variable
• RANK: creates rank variables
• AUTOMATIC RECODE: for automatic
recoding, like transformation of
string variables into nominal
variables
Statistics for Marketing & Consumer Research
Copyright © 2008 - Mario Mazzocchi
19
Data exploration
• Graphical plots of the data: to get a first overview of the
main characteristics of the data-set, especially the
distribution of the original variables across the whole
sample and for sub-samples
• Univariate descriptive statistics and one-way tabulation: to
synthesize the main characteristics of each of the variables
in the-set
• Multivariate descriptive statistics and cross-tabulation: to
get a first understanding of relationship existing between
different variables and enabling the joint examination of
two or more variables
• Missing data and outliers detection: to allow an early
detection of potential issues in subsequent analysis
Statistics for Marketing & Consumer Research
Copyright © 2008 - Mario Mazzocchi
20
Graphs
•
•
•
•
Univariate plots of
qualitative or discrete
data
Univariate plots of
quantitative data
Bivariate and multivariate
plots of quantitative data
Bivariate and multivariate
plots of quantitative
versus qualitative data
Statistics for Marketing & Consumer Research
Copyright © 2008 - Mario Mazzocchi
21
Univariate qualitative or discrete
data
Bar chart
Line chart
Sampled households by size
Number of sampled household by household size
200
200
150
Count
Count
150
100
100
50
Pie chart
50
Sampled households by household size
0
1
n=1
0
n=24
1
2
3
4
5
6
n=12
2
Household size
3
4
5
6
Household size
1
9
Household size
n=70
n=149
2
3
4
5
6
9
Pies show counts
n=67
n=177
Statistics for Marketing & Consumer Research
Copyright © 2008 - Mario Mazzocchi
22
9
Univariate continuous data (1)
Histogram
Number of sampled households by household income
Error bar chart
Household income by quartile
Error Bars show Mean +/- 1.0 SD
200 0.0 0
Box-Whiskers Diagram
Weekly household income plus allowances
50
200 0.0 0
25
0
100 0.0 0
200 0.0 0
300 0.0 0
Anonymised hhold inc + allowances
400 0.0 0
Anonymised hhold inc + allowan ces
Count
75
Maximum
150 0.0 0
Anonymised hhold inc + allowan ces
100
150 0.0 0

100 0.0 0

500 .00


0.00
Low i ncome
100 0.0 0
Medi um-h igh i ncome
Medi um-l ow in come
Hi gh income
Quartile
Median
Upper quartile
500 .00
Lower quartile
0.00
Minimum
Statistics for Marketing & Consumer Research
Copyright © 2008 - Mario Mazzocchi
23
Univariate continuous data (2)
Normal Q-Q Plot of EFS: Total Food & non-alcoholic beverage
Pareto charts
150
• Bars ordered in decreasing order of the
frequencies they represent
• The line indicates the cumulative proportion
• Useful for quality control (ANALYZE/QUALITY
CONTROL in SPSS) Pareto Chart
Expected Normal Value
100
50
0
100%
300000.00
-50
0
80%
200000.00
60%
40%
Percent
Anonymised hhold inc + allowances
Total Revenues by Income Quartile
Q-Q plots
100
200
300
Observed Value
• Compare the empirical (observed) data
distribution and some theoretical distribution
100000.00
170054.19
20%
78867.66
45640.06
0.00
High income
Medium-high
income
Medium-low
income
23488.32
Low income
Anonymised hhold inc + allowances
(Banded)
Statistics for Marketing & Consumer Research
Copyright © 2008 - Mario Mazzocchi
0%
• When the observed distribution is close to the
theoretical one, the plotted values tend to lie on
a straight line.
24
Bivariate and multivariate plots
Clustered Bar Chart
Scatterplot
Beer and sausage expenditure
Average household expenditure for selected categories by
income range
120.0
EFS: Total Food &
non-alcoholic
beverage
100.0
EFS: Total Clothing
and Footwear

EFS: Total
Recreation
80.0
Mean
Beer and lager (brought home)
75.000

Multi-variable Line Chart
Mean Weekly Household Expenditure by Category
with Confidence Intervals
60.0
EFS: Total Health expenditure
Low income
0.000











 



 







  








 


 

   



 
       










 



    
0.000
1.000
2.000
3.000
Medium-high
income

High income

EFS: Total Food & non-alcoholic beverage

EFS: Total Education
Multi-variable Pie Chart

4.000
Medium-low
income
Anonymised hhold inc + allowances
(Banded)

 

EFS: Total Furnishings, HH Equipment, Carpets
0.0


EFS: Total Housing, Water, Electricity
20.0
25.000

EFS: Total Recreation
40.0
50.000

EFS: Total Restaurants and Hotels
EFS: Total
Restaurants and
Hotels

EFS: Total Communication


EFS: Total Clothing and Footwear
Household expenditure by category

EFS: Total Alcoholic Beverages, Tobacco
5.000
EFS: Total Food &
non-alcoholic
beverage
Sausages
9.22%
11.84%
3.36%
10.16%
6.16%
1.93%
11.24%
16.89%
9.42%
2.88%
15.55%
1.35%
EFS: Total
Alcoholic
Beverages,
Tobacco
0.0
25.0
50.0
Value
EFS: Total Clothing
and Footwear
EFS: Total
Housing, Water,
Electricity
EFS: Total
Furnishings, HH
Equipment,
Carpets
EFS: Total Health
expenditure
EFS: Total
Transport costs
Cases weighted by Annual weight
Statistics for Marketing & Consumer Research
Copyright © 2008 - Mario Mazzocchi
25
75.0
Bivariate and multivariate plots
Pareto Chart
Stacked Pareto Chart
Total Weekly Expenditure for Selected Categories
50,000
Soft Drink and Fruit Juice Consumption
100%
1,400
Soft drinks
40,000
100%
80%
Fruit juices
1,200
10,000
Count
20,000
40%
800
60%
600
281
22,725
400
Clustered Bar Chart
6,335
0
200
0%
EFS: Total Restaurants and
Hotels
40%
20%
18,110
EFS: Total Food & non-alcoholic
beverage
80%
1,000
Percent
Count
60%
Percent
30,000
Cumulative
381
EFS: Total Alcoholic Beverages,
Tobacco
Alcohol expenditure away from home
20%
88
196
44
116
81
2
1
3
0
0
11
8
1
4
5
6
0%
Number of children
Means by income quartile
Wine from grape or
other fruit (away from
home)
8.000
Ciders and Perry (away
from home)
Mean
6.000
Beer and lager (away
from home)
4.000
2.000
0.000
Low income
Medium-low income Medium-high income
High income
Anonymised hhold inc + allowances (Banded)
Statistics for Marketing & Consumer Research
Copyright © 2008 - Mario Mazzocchi
26
Tabulation in SPSS
• Frequency tables
• Discrete, qualitative or banded metric variables
• Tables with descriptive statistics
• Cross-tabulation
• Joint frequencies for two discrete\qualitative variables
• Statistics for a metric variable by category of a nonmetric variable
• Multi-way frequency tables
Statistics for Marketing & Consumer Research
Copyright © 2008 - Mario Mazzocchi
27
Frequency table
Frequency Table for variable q1 in the Trust dataset
Response category
How many people do you
regularly buy food for home
consumption (including
yourself)?
Count
1 - Extremely unlikely
2
3
4 – Neither
5
6
7 - Extremely likely
Total
Missing values
Statistics for Marketing & Consumer Research
Copyright © 2008 - Mario Mazzocchi
91
176
100
94
21
13
2
497
3
%
18.3
35.4
20.1
18.9
4.2
2.6
0.4
100.0
28
Descriptive statistics
Descriptive statistics
In a typical
week how
much fresh or
frozen chicken
do you buy for
your household
consumption
(Kg.)?
446
54
In a typical
week how
much do you
spend on fresh
or frozen
chicken
(Euro)?
443
57
Age
500
0
Mean
1.0582
5.6677
45.582
Std. Error of Mean
.06843
.9100
.19640
5.0000
.7100
45.000
1.00
1.44514
3.00
4.13383
45.0
15.8763
2.088
.00
25.03
17.089
.00
30.00
252.055
18.0
87.0
25
50
.5000
.9100
3.0000
5.0000
32.000
45.000
75
1.3600
7.5000
57.000
N
Valid
Missing
Median
Mode
Std. Deviation
Variance
Minimum
Maximum
Percentiles
Statistics for Marketing & Consumer Research
Copyright © 2008 - Mario Mazzocchi
29
Cross-tabulation
Food & non-alcoholic beverage (Binned) * Anonymised hhold inc + allowances (Banded) Crosstabulation
Food & non-alcoholic
beverage (Binned)
£ 20 or less
From £ 20 to £ 40
From £ 40 to £ 60
More than £ 60
Total
Statistics for Marketing & Consumer Research
Copyright © 2008 - Mario Mazzocchi
Count
% of Total
Count
% of Total
Count
% of Total
Count
% of Total
Count
% of Total
Anonymised hhold inc + allowances (Banded)
Medium-low
Medium-high
Low income
income
income
High income
47
19
18
4
9.4%
3.8%
3.6%
.8%
57
48
24
22
11.4%
9.6%
4.8%
4.4%
17
31
45
40
3.4%
6.2%
9.0%
8.0%
4
27
38
59
.8%
5.4%
7.6%
11.8%
125
125
125
125
25.0%
25.0%
25.0%
25.0%
Total
88
17.6%
151
30.2%
133
26.6%
128
25.6%
500
100.0%
30
3-variables frequency table
Children, income and age of HRP
Number of children (Banded)
Anonymised
hhold inc +
allowances
(Banded)
Low income
Age of HRP anonymised
(Binned)
Medium-low
income
Age of HRP anonymised
(Binned)
Medium-high
income
Age of HRP anonymised
(Binned)
High income
Age of HRP anonymised
(Binned)
Statistics for Marketing & Consumer Research
Copyright © 2008 - Mario Mazzocchi
Less than 30 years
From 30 to 55 years
More than 55 years
Less than 30 years
From 30 to 55 years
More than 55 years
Less than 30 years
From 30 to 55 years
More than 55 years
Less than 30 years
From 30 to 55 years
More than 55 years
No
children
Table %
1.4%
2.6%
18.4%
1.0%
4.8%
12.0%
.6%
7.6%
6.4%
1.6%
9.2%
4.8%
One
children
Table %
.8%
1.0%
2.2%
.4%
.4%
2.6%
.4%
2.6%
Two
children
Table %
.2%
.4%
Total
More than
two
children
Table %
.2%
.2%
2.6%
.2%
1.6%
.8%
3.8%
.2%
.2%
2.4%
4.6%
.2%
1.6%
Table %
2.4%
4.2%
18.4%
1.4%
11.2%
12.4%
2.0%
16.4%
6.6%
2.0%
18.0%
5.0%
31
Quantitative by categorical
Books
Ice cream
Internet subscription fees
Cinemas
Age of HRP - anonymised (Binned)
Less than 30 years
From 30 to 55 years
More than 55 years
Standard
Standard
Standard
Mean
Deviation
Mean
Deviation
Mean
Deviation
.589 (1.59)
2.701 (8.26)
1.112 (3.78)
.000 (.00)
.067 (.39)
.010 (.11)
.263 (.96)
.396 (1.80)
.139 (.84)
1.240 (5.78)
.644 (3.37)
.107 (.84)
Statistics for Marketing & Consumer Research
Copyright © 2008 - Mario Mazzocchi
32
Detection of missing values
Cross-tabulation with a related variable (e.g. income by self-perceived wealth)
Total
Not very
well off
Difficult
Modest
Reasonable
Well off
Missing
SysMis
Income
Present
Missing
Count
342
23
33
114
117
53
2
Percent
68.4
88.5
76.7
74.5
63.9
65.4
14.3
% SysMis
31.6
11.5
23.3
25.5
36.1
34.6
85.7
• Non-response for income (31.6% in total) are not evenly distributed considering
self-perceived wealth: there is a larger proportion of NR for higher wealth levels
• Hypothesis testing methods (see lectures 6 and 7) may add statistical evidence
about non-randomness of missing values
Statistics for Marketing & Consumer Research
Copyright © 2008 - Mario Mazzocchi
33
Detection of outliers
• Outliers are anomalous values compared to other
in the sample
• They could be determined by:
• A measurement error
• A truly anomalous (exceptional) value with some specific
cause
• If a measurement error is ruled out, should outliers
be discarded or not?
• Answer: it depends upon whether anomalous
observations are relevant to the research
objectives
Statistics for Marketing & Consumer Research
Copyright © 2008 - Mario Mazzocchi
34
Dealing with outliers (1)
1) Define them
•
•
a value that is more than 2.5 standard deviations from
the mean
a value that lies more than 1.5 times the interquantile
range beyond the upper or the lower quartile
As the sample size increase the probability of having
anomalous values increases and their impact on
statistical analysis decreases
Hence one may wish to raise the above coefficient to
higher values (for example 4 standard deviations
instead of 2.5)
Statistics for Marketing & Consumer Research
Copyright © 2008 - Mario Mazzocchi
35
Dealing with outliers (2)
2) Detect them
• Graphically (scatterplots, boxplots)
• Check whether the combination of variables is
anomalous rather than having individual values
• Multivariate analysis, bivariate scatterplots, etc.
3) Decide what to do (according to objective and
subjective decisions)
• Delete outliers
• Correct outliers (similarly to missing values)
• Leave them alone
Statistics for Marketing & Consumer Research
Copyright © 2008 - Mario Mazzocchi
36
Outlier detection in SPSS
• E.g. Trust data set, variable q4kilos:
Mean:
Standard Deviation:
Upper quartile:
Lower quartile:
Interquartile range:
1.06 Kg
1.45 Kg.
0.50 Kg.
1.36 Kg.
0.86 Kg.
Outliers:
Value above 4.69 (mean + 2.5 times the standard deviation)
Or values above 2.65 (mean +1.5 times the interquantile range)
Statistics for Marketing & Consumer Research
Copyright © 2008 - Mario Mazzocchi
37
Exploring outliers
• Eliminate cases that are not outliers (e.g. below 4.69)
• Summarize cases left in the data-set with some variables
which could explain the outliers
Case Summaries
1
2
3
4
5
Total
N
Mean
In a typical
week how
much fresh or
frozen chicken
do you buy for
your
household
consumption
(Kg.)?
25.03
6.81
5.00
7.00
8.00
5
10.3680
• 5 outliers
In a typical
week how
much do you
spend on
fresh or frozen
chicken
(Euro)?
.00
.00
17.00
30.00
30.00
5
15.4000
Statistics for Marketing & Consumer Research
Copyright © 2008 - Mario Mazzocchi
How many
people do you
reg ularly buy
food for home
consumption
(including
yourself)?
5
6
3
5
5
5
4.80
• The first two are likely to be
response errors (expenditure is zero)
• The remaining three values seem
consistent with the expenditure and
the number of components
38
Outliers: scatterplots
Scatterplot

30.00
434
 
Scatterplot
Consumption and
expenditure
40.00
236


30.00

q5
price
188466
132
127
191
106
129
    
398
101
105
472
194
439
413
446
437
162
10.00
0.00
  
133
418
54
81
442
53
7128
 403
   454
384
177

31
26
76
402
102
104
107
167
417
424
113
116
131
157
169
173
302
323
409
490
112
185
263
425
431
452
470
115
137
147
443
461
192
 
80
48
184
4455
39
55
58
73
63
114
72
415
44
154
66
69
97
99
33
  484

38


 367
145
111
140
155
270
382
491
141
248
327

1
394
15
40
46
339
92
1193
89
56499
57
56
65
64
11 492
22
60
62
85
18
176
183
211
315
341
405
372
420
168
171
432
165
187
283
457
489
487
410
469
459
91
90 468
 356
103
13
182
271
332
362
338
427
333
74
79
126
125
153
220
235
239
249
358
408
429
444
456
460
27
50
68
98
120
422
108

 252
355


9438
32
  440
342
246
170
436
441
365
110
119
152
180
213
289
337
368
380
379
395
412
419
474
476
485
181
381
447
498
232
348
495
435
118
142
231
257
264
281
335
371
428
449
138
319
227
389
322
210





 240
250
201

87
70
202
330
28
77
6
12
14
262
268

 494
462
344
130
349
401
458
109
179
336
386
144
190
189
233
308
318
317
331
347
357
121
143
200
433
135
160
164
221
228
234
290
364
450
483
134
275
293
225
75



 387
346
295
286
352
224
229
288
383
253
255
261
292

304



 445
146
161
166
175
178
219
312
471
475
482
481
486
158
174
186
195
198
301
345
354
353
373
388
390
397
451
497
37
82
88
139
136
149
197
222
299
314
360
374
448
467
51
8
245
244
243
277
291
321
340
2
43
267
2
79
20
83
10
254

287
297
296
274
370
320
329
399
309
207
230
298
260
282

34




  477
124
123
218
242
272
276
306
311
316
343
350
378
196
479
256
259
280
325
351
385
209
226
247
269
285
20394
212
273

204
216
238
96
258
251
93
17
95

305
307
361
208
324
334
480
473
217
391
  393
49
  

23
465
29
59
84
36
414
47
3421
86
19
61
254245
0.00
20.00
10.00
78

100
10.00
20.00
q4
Statistics for Marketing & Consumer Research
Copyright © 2008 - Mario Mazzocchi

402
445
398





 

494
188
163
20.00
Consumption and prices
0.00
367
440
101
252
484

146
240
344
103
102
104
107
167
417
403
80

  38
127
352

355
436
441
18

 34
166
175
178
312
471
475
482
481
486
148
394
105

170
 251
387
176
183
211
315
356
322


349
401
458
462
13
145
342
 370

365
  219
161
182
271
332
133
418
434
466
341
405
31
130
106
184
424


  91
472

 361
307
124
123
274
311
316
343
477
158
174
186
195
301
345
354
353
373
388
390
397
451
497
87
109
179
336
386
110
119
152
180
213
289
337
368
380
379
395
412
419
474
476
485
362
372
420
113
116
131
157
169
173
302
323
409
490
194
439
1
32
4
39
55
58
73



210
250

70
202
330
63
114
455
191

 399
346
168
171
54
81

198
338
427
320
329
181
381
447


15
40
46

218
242
272
276
306
350
378
304
144
190
189
233
308
318
317
331
347
357
333
111
140
155
270
382
442


432


139
339
413
446
  305
491
3
454
84
498
224
229
288
383
165
187
283
457
489
487
196
479
37
82
88
121
143
200
433

112
185
263
425
431
452
470
273
201
74
79
72


309
232
348
495
204
216
238
136
149
197
222
299
314
360
374
448
467

126
125
153
220
235
239
249
358
408
429
444
456
460
415
437



254
410
92
26
76
393
435
16
89
177

141
193


53
208
324
334
480
207
230
118
142
231
257
264
281
335
371
428
449
115
137
147


28
77
44






  75
469
27
50
68
154
76162
 163
459
5
57
56
65
64




256
259
280
325327
351
385

135
160
164
221
228
234
290
364

98
120
422
248
499
6
69
97
99
443
461
128
9
32




90
253
255
261


93
246
129 236
 473
96
296
298
51
450
483
6
12
138
319
438
11
22
60
62
85
33
192
14
258
297
8
245
244
243
277
291
321
262
268

108

287
295
134
275
293

260
282
340
227
389

468

2
492

217
391
209
226
247
286
212
269
285

203
292

  17
43
267
279

20
83
23
 49
 95
 94
10225

29
59
84
36
414
47
3421
86
19
61
254245
100
0.00
78
10.00

20.00
q4
39