My first data analytics session at LBS was quite impactful and interesting. We discussed the meaning of data and how important it is to have accurate data because, as managers, we make decisions daily, and these decisions are not based on assumptions but facts. Thus, the quality of the analysis we carry out depends on the quality of the data we collect. In this blog post, I will focus more on basic statistical concepts.

Before I go into the statistical terminologies, let us explore the meaning of Statistics. Statistics is the collection, organization, presentation, analysis, and interpretation of numerical data in a meaningful way. The field of statistics helps us to make sense of otherwise meaningless numbers. If we make the data mean something, it becomes more useful to us. When business people refer to statistics, they usually discuss sales charts or business expenses. These statistics can be in the form of numbers or shown graphically. Now that we understand statistics, let us look at a few statistical concepts.

__Sources of Data__

Data can be classified based on so many sources from which it is obtained. When we collect data or our representative gathers data on our behalf to seek a resolution to specific statistical questions, such data is called **Primary** data. Examples of primary sources of data are interviews, questionnaires, etc. When we use data collected for someone else to answer statistical questions, we deal with **Secondary** data. Examples of secondary sources of data are books and journals, newspapers, and television programs.

__Nature of Data__

There are two types of variables for the data that is collected, and they are qualitative and quantitative data. Quantitative data or variables provide decisions based on numbers. This means we can conduct arithmetic operations on such data since it can be measured. Answers to questions like how many cars you own constitute quantitative variables because we can measure the answer to these responses. We deal with quantitative data with two types of data attributes: discrete and continuous. Discrete is usually an integer value, while continuous is a decimal value. An example of your age is a discrete attribute because age cannot be defined in decimal value. In contrast, an example of a continuous attribute would be temperature which can be described in a decimal value.

Qualitative data records a quality, character, feeling, perspective, or other attributes. Such data is always observed. Here, a number has arbitrary responses to questions like which type of car do you own does not result in a number but the car’s brand. Other examples of qualitative data may include responses to marital status, eye colour, gender etc.

__Population and Sample.__

**Population** refers to the collection or a set of all elements under study. It is the totality of the area where a sample will be collected. It is often a very large number, like a country’s population.

**A sample **is a subset or a small collection taken or drawn out from this population. Hence it is a smaller number and is most often taken as a population representative. It is the part of the population the data is collected from, and the conclusion is drawn.

Lastly, I would like to point out that statistics plays an important role in how we understand data, and numerous ethical issues can present themselves when the data is collected, analyzed, and presented. As a manager or student of statistics, you must be fair, thoroughly objective, and neutral as you conduct your research. Also, as a consumer of statistics, you should be wary of unscrupulous information sources and unethical statistical behavior. Consider the source of information when evaluating statistics produced by others and available to the public.

There are many other statistical concepts; however, we will continue in our subsequent posts.

#MEMBA11

**Written by Tutty Tero**