Data summaries and groupings - Information technologies in marketing

Data summaries and groupings

Statistical summaries and groupings of data are used to process marketing information.

Summary is the stage of statistical research, during which the primary materials of statistical observation are systematized, data are grouped, tables are compiled, group and total results are counted, and mean and relative values ​​are calculated. It allows us to proceed to generalizing indices of the whole as a whole and its individual parts, to carry out analysis and forecasting of the processes under study.

The organization and conduct of the report includes four stages:

• checking the source data;

• grouping of data by specified characteristics;

• Development of a system of statistical indicators;

• registration of summary results in the form of statistical tables, convenient for the perception of information.

Checking the original data involves monitoring the results of information to eliminate errors and data illogicality. For example, when analyzing the capacity of the regional beer market, the figure is 5 liters, which is illogical. Another example of a combination of arithmetic and logical mismatch is presented in Table. 5.4.

In order to solve a number of specific problems, to reveal features in the development of phenomena, to detect trends, to establish dependencies, it is necessary to group the statistical data. The data are grouped according to the summary program in order to subsequently provide the information received in a form that is accessible to perception.

Table 5.4

Company Profile

Age, years

Total length of service, years

Continuous experience, years

20

2

1.5

30

10

12

40

21

18

50

47

48

Thus, grouping is the union of the aggregate units into certain groups that have their own characteristics, common features and similar dimensions of the trait under study. For this purpose, a grouping feature is selected and a system of summary indicators is developed that will characterize the selected groups. The definition and justification of indicators depends on the purpose of the study.

A special kind of groupings is the classification , which is a stable nomenclature of classes and groups formed on the basis of similarities and differences in the units of marketing objects being studied. The classification is in the form of a statistical standard, set for a certain period of time.

The grouping method is used to solve the following tasks:

• highlighting types of marketing phenomena;

• study of the structure and structural shifts of the phenomenon;

• the study of relationships and dependencies between phenomena.

The grouping results are arranged in the form of grouping

tables, making information foreseeable, for example, a grouping table of consumers (Table 5.5).

Table 5.5

Results of the analysis of the consumers of the goods A by the women of the city M at the age of 20-25 in the N year

Women

I do not consume

Sometimes I consume

I consume

I consume

often

Workers

1

4

8

3

Employees

2

25

39

7

Housewives

4

32

51

1

Total

7

61

98

11

Groupings are distinguished depending on the tasks involved.

By the number of grouping characteristics distinguish simple (by one feature) and complex (by several features), combined and multidimensional groupings.

Combined groupings are constructed by splitting each group into subgroups in accordance with additional characteristics; multidimensional - with the help of special algorithms, when a cluster is searched for in an N-dimensional space, where each object is a point, i.e. build a multidimensional grouping - find a cluster of points.

For systematization of data allocate typological, structural and analytical groupings.

To include all groups that characterize the qualitative features and differences between types of phenomena. Typological groupings are intended to identify qualitatively homogeneous groups of populations, i.e. objects close to each other at the same time for all grouping characteristics. For example, a grouping of city enterprises by types of goods sold. The most essential features that directly characterize the essence of phenomena should be taken as the basis of the grouping. Groups should be justified from a marketing point of view. An example of a typological grouping about the age composition of the population in the city N is presented in Table. 5.6.

Table 5.6

Analysis of the age composition of consumers, %

Consumer

Age, years

Up to 18

18-25

25-30

30-35

Workers

17

17.6

50.2

68.3

Employees

14

12.4

33.5

49.5

Villagers

16.3

4.6

2.1

1.5

Structural groupings - the division of a homogeneous aggregate into groups that characterize its structure according to a certain grouping characteristic. Such groupings are of great importance for studying the structure of the same phenomena. An example is the grouping of trade enterprises by type of product, the number of employees, turnover, the grouping of sales personnel by qualification, etc.

Analytical groupings are designed to identify the relationship between the signs. Using analytical groupings, determine the factor and effectiveness indicators of the phenomena being studied. Factor - these are the signs that affect other related characteristics. Effective - signs that change under the influence of factorial.

In order to investigate the relationship between the selected features using the method of analytical groupings, it is necessary to group the units of the population according to a factor characteristic and calculate the average values ​​of the effective trait for each group, the variation of which from group to group will indicate the presence or absence of the relationship. >

Based on the information used, distinguish between primary and secondary groupings.

Primary groupings are produced on the basis of the initial data obtained as a result of statistical observations. Secondary is the result of the union or splitting of the primary grouping.

In developing a primary grouping, the choice of the number of groups is essential. The number of groups depends on the type of attribute underlying the grouping, on the volume of the population, the degree of variation of the characteristic.

When constructing groupings according to the qualitative characteristic, the number of groups corresponds to the number of gradation levels of the characteristic. When grouping by the quantitative characteristic, the entire set of characteristic values ​​is divided into intervals. Two approaches are possible: grouping with equal and unequal intervals.

To determine the optimal number of groups ( t ) at equal intervals, Stargess's formula is recommended:

where N - the number of observations or the number of units of the population.

In this case, the value of equal intervals

where Xmax, Xmjn - respectively, the maximum and minimum values ​​of the characteristic in the aggregate; and the boundaries of the intervals

where Χ nti , X bi - respectively the lower and upper boundaries of the interval; i is the ordinal number of the interval (i = 1, 2 ..., t).

Grouping with uneven intervals generates a lot of problems when processing data, so avoid such grouping as much as possible. For example, there are data on the work of the same type of trade enterprises for the implementation of a particular type of product (Table 5.7).

Estimated Data

Table 5.7

Commercial company code

Sales, million rubles.

Market share,%

1

3.2

6.5

2

9.6

25.6

3

1.5

2.4

4

4.1

5.3

5

3.8

12.2

6

6.1

7.3

7

9.1

28.5

8

1.4

4.2

9

2.7

2.1

10

3.3

5.9

We set the task to identify in this sales system the distribution of enterprises by turnover and the effect of this trait on the size of the market share.

Then m = 1 + 3.21 lgl0 = 4.21, we take m = 4. This means that D = (X Xmin) /m = (9.6 - 1.4)/4 = 2.05.

Let's create a preliminary working table. 5.8.

Table 5.8

Preliminary grouping of sales enterprises by sales intervals

The interval of product sales, million rubles.

Cipher

Enterprise

Sales, mln

rubles

Market share, %

1.4-3.45

1

3.2

6.5

3

1.5

2.4

8

1.4

4.2

9

2.7

2.1

10

3.3

5.9

Total

5

12.1

21.1

3.45-5.5

4

4.1

5.3

5

3.8

12.2

Total

2

7.9

17.5

5.5-7.55

6

6.1

7.3

Total

1

6.1

7.3

7.55-9.6

2

9.6

25.6

7

9.1

28.5

Total

2

18.7

54.1

The group indicators of the working table are entered in the corresponding rows and columns of the table layout and we obtain the final consolidated group table with the results of the grouping of the sales companies and the market share of the product (Table 5.9).

Table 5.9

Final grouping table

The interval of product sales, million rubles.

Enterprise

Sales and Distribution

Market share

number

% to total

million rubles.

% to total

%

% to total

1.4-3.45

5

50

12.1

27.01

21.1

21.1

3.45-5.5

2

20

7.9

17.63

17.5

17.5

5.5-7.55

1

10

6.1

13.62

7.3

7.3

7.55-9.6

2

20

18.7

41.74

54.1

54.1

Total

10

100

44.8

100

100

100

Table 5.9 shows that 20% of retailers with a sales range of 7.55-9.6 million rubles. have a 54.1% market share.

Rearranging the previously grouped data is called secondary grouping. In this case, the intervals are enlarged or reduced. It is used to bring groupings at different intervals to a comparable species in order to compare them. For example, the situation of the purchasing power of the population of the districts N and M is given in Table. 5.10.

Table 5.10

Group buyers by the amount of one-time purchase of products in stores of the same network

District N

Area M

One-time purchase, RUR.

Number of consumers,%

One-time purchase, RUR.

Number of consumers,%

100-300

16

100-500

10

300-600

14

500-1000

20

600-900

40

1000-1500

40

900-1200

25

1500-2000

30

1200-1500

5

-

-

Total

100

Total

100

The given data do not allow to compare distribution of consumers on the sum of purchase in a store of a trading network as there are various number of groups of consumers and various sizes of intervals. We perform the secondary grouping by the method of strengthening the intervals, forming the same number of groups and with the same intervals as in the second region (Table 5.11).

Table 5.11

Secondary customer grouping by purchase value

Group by the size of a one-time purchase of goods, rubles.

Specific weight of consumers,%

Calculation

Area M

District N

100-500

10

23

16 + 0.5 • 14 = 23

500-1000

20

55

14 • 0.5 + 40 + 0.33 • 25 = 55

1000-1500

40

22

0.67 • 25 + 5 = 22

1500-2000

30

-

-

Total

100

100

100

Analysis of the consumers of the district M suggests that they have a higher purchasing power than in the area N (purchase for the amount of 1000-1500 rubles is possible in 40% consumers in the area M and only in 22% in the area N).

Also We Can Offer!

Other services that we offer

If you don’t see the necessary subject, paper type, or topic in our list of available services and examples, don’t worry! We have a number of other academic disciplines to suit the needs of anyone who visits this website looking for help.

How to ...

We made your life easier with putting together a big number of articles and guidelines on how to plan and write different types of assignments (Essay, Research Paper, Dissertation etc)