In data analysis, a distinction is made between two main types of data or variables: quantitative data and qualitative data. There is a significant difference between quantitative and qualitative data. Both models are widely used in data analysis. To get the most out of them, it is essential to master them in order to carry out a relevant analysis of the data and draw better conclusions, we tell you more in this article!
Quantitative or numerical data
In data analysis, quantitative or numerical data refers to quantifiable information or characteristics that take numbers as their value. Quantitative data is structured and perfectly suited for data analysis. The number of employees in a company, age, weight, height, temperature, time, area, turnover of a company are all examples of quantitative data. Quantitative data can be represented by means of tables, diagrams and graphs. Here you will understand the difference between structured and unstructured data.
Types of quantitative data in data analysis
In data analysis, there are two main models of quantitative data: continuous quantitative data and discrete quantitative data.
Continuous quantitative data
A quantitative data is said to be continuous when it takes an infinite number of real values within a given interval. The height of a person is an example of continuous quantitative data. Even if it cannot take on all possible real values, it can take on an infinite number of values within a defined interval depending on the object being measured. The weight of a person, the height of a building are also examples of continuous quantitative data. Between two weight values, for example, there are millions of possible weights. In general, the data that comes from a measurement is quantitative.
Discrete quantitative data
In statistical studies, discrete quantitative data are data that can only take a finite number of possible real values within a given interval. They cannot therefore be reduced to smaller parts. This is wherediscrete quantitative data differs from continuous quantitative data. The number of employees in a company or the size of a household are examples of discrete quantitative data.
The number of employees in a company is also a discrete quantity. Taking the example of companies with at most 100 employees, the number of possible values for such a variable cannot exceed 100, since it is known that it is impossible for a company to have a number of employees that is a fraction of a whole number, such as 60.9.
The process of analysing quantitative data?
Theanalysis of numerical data takes place in the context of a quantitative study. The first step is always the collection of data or information.
Whether discrete or continuous, quantitative data can be obtained through a method or strategy such as survey or controlled observation. Surveys, longitudinal studies and telephone or face-to-face interviews are also commonly used methods and techniques for collecting quantitative data.
The next step is data processing. In this phase, the collected data is put into a new format in order to be analysed more efficiently. The analysis can then begin. The collected data can be cross-referenced in the form of a graph or table. These results are then analysed using software and statistical tools. Conclusions are then drawn for the study.
Qualitative or categorical data
Qualitative or categorical data refers to a non-quantifiable characteristic, most often derived from a count. In contrast to quantitative data, qualitative data does not provide figures that can be represented graphically. This data is used in particular to classify responses according to properties and attributes.
Qualitative data are often interpreted in simple language. They are used to describe information, characterise objects or observations. Their descriptive nature makes them more difficult to analyse.
The use of qualitative data allows researchers and companies to better understand the behaviour, personality and emotions of their respondents. Similarly, in market research, for example, qualitative data plays a key role in helping researchers better understand their customers. Knowing what motivates customers through qualitative data helps brands make better business decisions.
Types of qualitative data
In data analysis, qualitative data can be divided into two broad categories: nominal qualitative data and ordinal qualitative data.
Nominal qualitative data
Nominal qualitative data describes a name or category in no particular order. Nominal qualitative data are mainly used to label variables. This is why they are sometimes called labels. Examples of nominal qualitative data are the mode of transport used by the employees of a company, the gender, the colour associated with a brand.
Ordinal qualitative data
Ordinal qualitative data is data that has values defined by an order relationship between the different possible categories. An example of ordinal qualitative data is the assessment by customers of the quality of a company's services. It has categories such as "Good", "Very good", "Excellent" between which an obvious order relation can be established. The "Very good" category is better than the "Good" category, but less interesting than the "Excellent" category. The ordinal qualitative data have a shortcoming, however. Even if an order can be found, it is not possible to know to what extent one category is better than the other.
How to collect qualitative data?
Qualitative data are highly valued in social science research such as sociology. Different methods are used to collect them from a sample of a given population. These include individual interviews, focus groups, case studies, open-ended survey questions and observational research.
The survey can also be used to collect qualitative data. Interviews, for example, allow for a better analysis of a hypothesis, particularly through an individual approach. Focus groups allow several people to express their ideas and opinions on a given subject. Case studies provide companies with consumer feedback.
Training in data analysis
People who want to learn more about the different types of data can turn to a data science course like the one organised by Jedha. Jedha's data science courses are at the top of the list of the best data courses in France. Particular emphasis is placed on the quality of the trainers in order to provide students with the best possible learning experience. Jedha data science courses can be done full time, part time, face-to-face or distance learning to offer learners more flexibility.