# Classification of Data | Business Statistics Notes | B.Com Notes Hons & Non Hons | CBCS Pattern

B.Com 2nd and 3rd Semester (CBCS Pattern)

## Classification of Data

The process of arranging the data in groups or classes according to their common characteristics is technically known as classification. Classification is the grouping of related facts into classes. It is the first step in tabulation.

In the words of Secrist, "Classification is the process of arranging data into sequences and groups according to their common characteristics or separating them into different but related parts."

Essentials of classification

a) The classification must be exhaustive so that every unit of the distribution may find place in one group or another.

b) Classification must conform to the objects of investigation.

c) All the items constituting a group must be homogeneous.

d) Classification should be elastic so that new facts and figures may easily be adjusted.

e) Classification should be stable. If it is not so and is changed for every enquiry then the data would not fit for an enquiry.

f) The data must not overlap. Each item of the data must be found in one class.

According to nature, data may be classified as:

1. Univariate data: Univariate data is a data in which there is only one variable. It is simplest form of data and deals with only change in quantity. It does not deal with cause and effect relationship between two or more variables. The main purpose of univariate data is to find the pattern exist in given data. Examples of univariate data is age of 10 workers in a factory, marks scored by 50 students in mathematics etc. Pattern exists in univariate data can be analysed with the help of various tools of measures of central tendency and dispersion. Also diagrams and graphs can be used to analyse univariate data.

2. Bivariate data: Bivariate data is a data in which there are two different variables. It deals with cause and effect relationship between two variables and analysis of data is done to find the relationship between two variables. Example of Bivariate data is age and weight of workers, demand and supply of a product, marks of students in two different subjects, temperature and sales of woolen products etc.

3. Multivariate data: Multivariate data is data in which there are three or more variables. Example of multivariate data is suppose a manufacturer wants to compare the sales data of his product in five different areas. Some of the common tool used to analysed multivariate data is correlation and regression analysis, multivariate analysis of variance etc.

4. Time series data: Time series data is the study of behaviour of single variable at different intervals. This data is analysed to find the trend. Example of time series data is the sales of product X over a period of 10 years.

5. Cross sectional data: Cross sectional data is the study of behaviour of more than one variable at different interval.  Example of cross sectional data is the sales of product X over a period of 10 years in four different states.