In ancient times, land was the most important and valuable things called asset in the world.
In the mordent era, factories and machines became more important than land. Now, in the 21st century, data is the most important asset compared to land machinery.
In today’s digital world, data is the most valuable asset of our society. It is everywhere. For example, when you send a message using your smartphone, this is an example of text data.
Every system produces data, whether it is the smallest smartphone app or the largest enterprise software. The rate at which data is being producing per day is tremendous.
Every company, such as Google, Facebook, Walmart, Amazon, etc. is using data to perceive their customer better. Therefore, it is important to understand what data is, types of data, how any company collects and analyzes it.
In this tutorial, we will understand what is data, and its types with the help of realtime examples.
What is Data?
In today’s technology-driven world, data is undoubtedly the most valuable asset for an organisation.
Data is a collection of information, facts, or statistics that is used for analysis and decision-making purpose. It is an essential thing in all fields of life, such as business, science, healthcare, education, etc.
We always need data for analysis and decision making, from research community to business markets. It comes in different forms, such as text, numbers, pictures, or videos. We are producing bulk of data on the daily basis in all over the world.
For example, whenever, we type a text message, upload an image, browser a web, typing a message on social media platform, we are producing a lot of data which is being stored somewhere,(e.g. on servers) and available for processing.
An amount of data is increasing at the rate of hundreds of thousands of tons every second. We can collect it from various sources, such as surveys, observations, or sensors.
Types of Data
Now, it is important to understand different types of data for several reasons. We can divide data into three basic categories:
- Structured vs Unstructured
- Quantitative vs Qualitative
- Four levels of data
Let’s understand each category with the help of simple examples.
Structured data is data that is usually organised and well-formatted using table method (rows and columns). We can easily search and access information from the structured data.
Sometimes, it is also called organized data. We can easily store structured data in tables within databases or Excel files.
SQL, or Structured Query Language, is the best example for structured data where we can store data in the form of tables having multiple rows and columns.
It is the preferred way to manage and query data that resides in databases. Structured data is only 7 to 10% of all data in the world. Another good example of structured data is the spreadsheet.
A familiar example of structured data is customer information. An e-commerce company has a customer database that is structured data, with each row representing a different customer and columns representing customer details such as name, phone number, email, address, and purchase history.
Here’s a simple example of a table for structured data, with each row representing a different customer and columns representing customer details such as name, phone number, email, address, and purchase history:
Unstructured data is data that exists as a free entity and does not fit into any data model. This type of data does not follow any standard organisation hierarchy.
Since unstructured data does not organize and easily classify in a predefined manner, therefore, it is also called unorganized data. It is often qualitative in nature. It needs advanced tools and software to access information or data.
A very familiar example of unstructured data is your regular email. An email message typically contains unstructured data, with the content of the email not following a predefined format.
The body text can include a wide range of information, from formal business communications to informal chats. However, an email contains structured elements such as the title, sender, and body text.
Also, a person may organize its inbox in such a way that it aligns with their organisational preferences, but it does not mean the text data is structured.
Quantitative data is a type of numerical data or values that we collect and analyze to gain meaningful insights in the field of statistics.
We can collect it through various methods, including surveys, experiments, and observations. We can analyze this type of data using statistical methods to uncover patterns, trends, and relationships within the data.
There are two types of quantitative data: discrete and continuous.
It is a type of quantitative data that only takes on specific values. For example, the number of children in a family, the number of pets in a household, or the number of cars in a parking lot are some familiar examples of discrete data. We count or measure discrete data in whole numbers.
It is a type of quantitative data that takes on any value within a range. For example, weight, height, and time are some familiar examples of continuous data. We usually measure continuous data using a scale or measuring device.
Qualitative data is a type of non-numerical data that we collect and analyze to draw meaningful insights in the field of research.
We often use this type of data in research, social sciences, and humanities to explore complex topics as well as understand the experiences of individuals and groups.
With the help of various methods, including interviews, focus groups, observations, and document analysis, we can collect qualitative data.
We can analyze this type of data using various qualitative research methods to uncover themes, patterns, and relationships within the data.
There are several types of qualitative data that are as follows:
We collect interview data through interviews with individuals or groups. It can be structured or unstructured. We often use it to explore personal experiences, beliefs, and attitudes.
Focus Group Data:
We collect focus group data through group discussions. We often use it to explore group dynamics and opinions about a particular topic or product.
We collect observational data through observations of individuals or groups. Generally, we use it to explore behavior and interactions in natural settings.
We collect documentary data through the analysis of documents, such as newspapers, reports, and historical records. We usually use this type of data to explore social and historical contexts.
Four Levels of Data
We can also break down a specific characteristic (feature or column) of structured data into one of four levels of data. The levels are as follows:
- Nominal level
- Ordinal level
- Interval level
- Ratio level
Nominal level is a type of data measurement where data is grouped or categorized based on specific characteristics.
In other words, it is a type of data that we use to group or classify objects, people, or events based on specific characteristics (feature or column). It is also known as categorical data.
We describe nominal data purely by name, category, or level that does not have any inherent order or ranking. Basic examples of nominal level data are nationality, gender, ethnicity, martial status, occupation, favorite color, etc.
In each of these examples, we can categorize the data into distinct groups or labels. For instance, we can categorize gender data as male or female and ethnicity data as Asian, African, or European. Since we cannot describe them by numbers, therefore, they are qualitative data.
Ordinal level is a type of data measurement where the data is ranked or ordered based on a specific characteristic. In other words, it is a type of categorical data where the categories have a specific rank order.
Familiar examples of ordinal data include:
- ranks in a competition
- education levels
- income levels
- satisfaction levels
We can order each of these examples from lowest to highest based on the specific characteristic or attribute being measured. We commonly use ordinal data in surveys and questionnaires to measure attitudes or opinions.
Interval level is a type of data measurement that involves numerical values measured on a continuous scale. At the interval level, the difference between the two values is meaningful, as well as a fixed interval between any two values.
This type of data measurement differs from nominal and ordinal levels, where the values are discrete and categorical, respectively.
The interval level of data can be positive or negative based on an arbitrary zero point. For example, temperature is a familiar example of data at the interval level.
If it is 100 degrees Fahrenheit in New York and 80 degrees Fahrenheit in Dhanbad, India, then New York is 20 degrees warmer than Dhanbad.
Some familiar examples of data at interval level include:
- Temperature measurement (in Celsius or Fahrenheit)
- Time measurement (hours, minutes, seconds)
- Calendar dates
- Scores on an exam
- IQ test scores
Ratio level is a type of data measurement that involves numerical values measured on a continuous scale and has an absolute zero point.
It is a significant and strongest measurement level in all of four levels that provides accurate and meaningful insights into numerical data. We often use it to measure physical quantities, such as weight, height, distance, and time.
Some familiar examples of ratio level data are :
- Weight measurement (in pounds or kilograms)
- Height measurement (in inches or centimeters)
- Time measurement (in seconds or minutes)
- Distance measurement (in meters or miles)
- Speed measurement (in miles per hour or kilometers per hour)
In this tutorial, you have known about what is data, and its type with the help of realtime examples. Hope that you will have understood the basic points and enjoyed this tutorial.
Thanks for reading!!!