In the method of statistical groupings, the totality of the studied phenomena is divided into classes and subclasses, which have a homogeneous structure according to certain characteristics. Each such division is described by a system of statistical indicators. Grouped data can be presented in tables.
This action is the main method used in the actual study of social phenomena. It arises as a prerequisite for the application of various groupings of statistics, procedures and analytical methods. For example, classification is necessary in order to use any generalized indices, such as averages.
Contribution of V. I. Lenina
In pre-revolutionary Russian statistics, in particular, in various zemstvos (these are local governments), significant experience was gained in grouping different types of organizations. And also at that time, significant work was done to develop not only tables with classification one by onecharacteristics, but also more complex schemes. In them, all data is grouped by two or more parameters. However, theoretical issues related to the use of statistical grouping methods have not received scientific justification. This state of affairs persisted until the works of V. I. Lenin. He had a high opinion of the cognitive value and practical importance of classification. With regard to tables based on the signs of a statistical grouping of more than one characteristic, Lenin wrote: “It can be said without exaggeration that they will revolutionize science and, of course, agricultural economics.”
Vladimir Ilyich's recommendations on the need for a preliminary political and economic analysis of the nature of patterns and determining the types of phenomena before starting experiments with the classification of initial data are of fundamental importance.
Stages of statistical groupings
Systematization is used not only in the analysis of the structure of the population, but also in determining the types of phenomena and in the study of the relationship between various characteristics or factors. Examples of groupings that express population structure are classifications of people by age (at intervals of one year or, more commonly, five years) and businesses by size.
By combining classes or setting uneven intervals, it is possible to establish qualitative differences between individual systems, and then determine the techno-economic or socio-economic types of the relevant subjects(for example, enterprises or farms). Thus, the grouping of the population of a country by age can be carried out on the basis, in addition to simple chronological objects, of such special divisions as women aged 16 to 54 years and men aged 16 to 59 years. The use of these special classes makes it possible to calculate the national economic index, known as the country's labor force. The interval boundaries are somewhat arbitrary and may differ from state to state.
Task
Detailed quantitative classification of enterprises and firms allows us to proceed to the definition of several basic qualitative groups, such as small, medium and large organizations. After that, a number of general economic problems can be clarified, for example, the process of concentration of production, the growth of industrial efficiency and the increase in labor productivity. Vladimir Ilyich Lenin's new data on the laws governing the development of capitalism in agriculture is a brilliant example of deep analysis that uses grouping to demonstrate the complex nature of patterns. And also the relationship between the size of the enterprise and its overall productivity.
The most important and difficult task of statistical groupings is to identify and describe in detail the types of socio-economic phenomena. Such subjects represent the expression of forms of a certain social process or basic characteristics. They seem to be common to many individual phenomena. In his analysis of the stratification of the peasantry, Vladimir Ilyich Lenin used the groupingthoroughly and comprehensively. First of all, he revealed the process of formation of the main social classes in pre-revolutionary Russia, in the Western European countryside and in US agriculture.
And, as it turned out, Soviet data have considerable experience in typological and statistical groupings. For example, the balance sheet of the national economy of the USSR presupposes a complex and branched system of classification. Other examples of typological statistical grouping in the Soviet space include the systematization of the population by social class. As well as the unification of fixed production assets by socio-economic types of industrial units. And you can also give such an example as the grouping of the statistical population of the social product.
Bourgeois classification does not use systematization enough. When grouping is used, it is for the most part incorrect and does not contribute to characterizing the true state of affairs in the capitalist countries. For example, the classification of agricultural enterprises by land area exaggerates the position of small-scale production in this vein. And the grouping of the population by profession does not reveal the true class structure of bourgeois society.
The socio-economic characteristics of a socialist state provide new applications for statistical grouping. The classification is used to analyze the implementation of national economic plans, to determine the reasons for the lagging behind of some enterprises and sectors. And also identify unused resources. For example, businessescan be grouped according to the degree of implementation of the plan or the level of profitability. Of great importance for characterizing the introduction of scientific and technological progress into industry is the grouping of enterprises, according to such technical and economic data as the degree of automation and mechanization and the amount of electricity available for work.
Grouped data is information formed by combining individual groupings of statistical observation about the presence of a variable into separate classes, so that the frequency distribution of these systems serves as a convenient means of summarizing and analyzing all materials.
Information
Data can be defined as groups of material that represent qualitative or quantitative attributes of a variable or set of variables. This is analogous to saying that classes can be any set of information that describes an entity. Systems, in the grouping of statistical data, can be classified into grouped and non-grouped objects.
Any information a person gathers first is unclassified. Ungrouped statistical groupings are data, but only in an unprocessed form. An example of such systems is any list of numbers you can think of.
First type of classifications
Grouped data is information that has been organized into groups known as classes. This type has already been classified, and thus somelevel of analysis. This means that all information is no longer raw.
A data class is a group that is associated with a specific custom property. For example, if the manager of an enterprise collected the people he hires in a certain year, he could group them into systems by age: twenty, thirty, forty, and so on. And each of these groups is called a class.
In turn, this is not the last division. Each of these classes has a certain width and this is called spacing or size. This concept is very important when it comes to plotting histograms and frequency plots. All classes can have the same or different sizes, depending on how all the information will be grouped. The system interval is always an integer.
Class constraints and boundaries
The first concept refers to the actual values that can be seen in the final table. The class constraints fall into two categories: the lower limit of the system and the upper limit. Of course, all divisions in the tables are used to ensure correctness and informativeness.
But, on the other hand, class boundaries are not always respected in the frequency table. This concept gives the true interval of systems and, like various restrictions, is also divided into boundaries of the lower and upper values.
Living and non-living bands
Science seeks to understand and explain natural phenomena. Scientists understand things by classifying them. It belongsboth living beings and non-living groupings of statistical materials.
In turn, these types can be divided into groups depending on the contrast properties. For example, if students have compiled lists in their scientific journals about the various materials and subjects they have studied, they can use this data to expand knowledge and information about the systems they have studied.
All knowledge can be sorted or classified according to various contrast properties. Here are some examples:
- Metals versus various non-metals.
- Stony terrain instead of desert or meadow.
- Visible crystals vs invisible minerals.
- A natural process instead of an artificial one.
- Substances denser than water or less weighty than a given liquid.
- Magnetic versus non-magnetic.
And you can also make group differences according to the following features:
- The state of matter at room temperature (solid, liquid, gas).
- Fusibility of metals.
- Physical properties and so on.
Materials:
- Various articles that exemplify the categories above.
- Magnets for testing the properties of materials.
- A container of water to check whether things float or sink.
- Scientific journals.
Operating procedure
Exactly how things happen:
- Students work in groups. Each is given some materials and asked to find ways to groupitems by category. They develop the criteria they will use and then sort the items accordingly. Tables of results are recorded in their scientific journals.
- After grouping the materials, they are sorted again according to other criteria. The next step will also be compiling a list of results. And after that, an additional row of elements is written, which were sorted differently due to changing criteria.
- Students record observations and tables in their scientific journals.
Results
Students fix a series of tables that show how their subjects are sorted based on each of the criteria. For example, a group of students has a paper clip, a small piece of granite, a cork, a plastic toy. And then a pair of sorting tables might look like the following.
-
Items sorted by magnetism.
React to magnet: paper clip, granite. Not responding: cork, plastic.
-
Items sorted by density compared to water.
Pop up: cork, plastic. Drowning: paper clip, granite.
After that, students make presentations to the class. They discuss why different items are classified differently based on the criteria used.
Students repeat these observations each time, applying different properties.
Talk
At this stage:
- Students can extend these observations to other materials without anypractical research.
- Examples are samples of different types of rocks. Students will learn how to make closer observations and write exactly what they see with magnifiers and other items they use.
- If students have created an index file of properties written on cards, they can also be sorted. This will be useful if the index contains additional materials that are not in the class.
A common way to process continuous quantitative data is to subdivide the entire range of meanings into several subranges. It is necessary to assign to each material a constant value of the class in which it falls. Note that the data set changes from continuous to discrete.
The concept of statistical grouping
Organization is done by defining a set of ranges and then counting the amount of data that falls into each of them. The subranges do not overlap. They must cover the entire range of the data set.
One of the most successful ways to visualize grouped systems is the histogram. It is a set of rectangles where the base of the shape spans the values in the range associated with it. And the height corresponds to the amount of information.
