Data analysis is a process of collecting, inspecting, cleaning, transforming, and modeling data to discover useful information and get helpful conclusions for business decision-making. A person who evaluates data using analytical or statistical tools to discover useful information is known as a Data Analyst. The process of presenting data in visual form is known as Data Visualization.
The main purpose for analyzing data is to extract useful information from raw data and then take a decision based on facts from the analyzed data, since data analysis relies on methods and techniques to take raw data and mine them for insights that are relevant to the business’s primary goals.
Why Data Analysis?
Data-driven businesses and organization constantly make decisions based on data and facts, this way, they can be more confident in taking actions guaranteed to bring success, since there is an available data to support them.
Since many individuals, organization and businesses rely on helpful data and facts, through research to make more strategic decisions that helps their businesses and organization operate more effectively so as to avoid making avoidable mistakes, a data analyst is required to do data analysis to help analyze data, gather all useful information and provide all necessary details needed to make the right decisions.
Data analysis today is used by small businesses, off and online retail companies, in medicine, and even in the world of sports.
Methods and Techniques
While a variety of methods are used for data analysis including data mining, text analytics, business intelligence, combining data sets, and data visualization, they are all based on two major categories namely; Qualitative and Quantitative Analysis.
This video from YouTube will further help you understand better between quantitative and qualitative data analysis methods.
Qualitative analysis is a method of data analysis that mainly answers questions seeking for answers. Questions such as why, what or how, are usually addressed via quantitative techniques such as questionnaires, standard outcomes, attitude scaling and more.
These types of analysis are mainly in the form of texts documents and narratives, and can sometimes include the use of audio and video representations.
Generally, this analysis is measured in terms of numbers. The data here present themselves in terms of measurement scales and extend themselves for more statistical manipulation.
Types of Data Analysis
There are several types of Data Analytics methods and techniques that are in use across all industries based on business and technology needs.
However, the five major types of data analysis are:
- Text Analysis.
- Statistical Analysis: Inferential and Descriptive Analysis.
- Diagnostic Analysis.
- Predictive Analysis.
- Prescriptive Analysis.
Also referred to as data mining, text analysis is a technique to analyze texts to extract machine-readable facts and discover a pattern in large data sets using databases or data mining tools. The main objective of text analysis is to create structured data out of unstructured and free content into business information.
As the name implies, statistical analysis is the technique of performing several statistical operations such as collection, Analyzing, interpretation, presentation, and modeling of data to quantify the data, know what happened from past data and then apply statistical methods.
To perform statistical analyses, various tools such as SAS (Statistical Analysis System), SPSS (Statistical Package for the Social Sciences), Stat soft, and more are required.
The data in this type of analysis is usually descriptive; like surveys and observational data. Many data analyst like to refer to it as a descriptive analysis, even though there are two categories of this type of Analysis namely; Descriptive and Inferential Analysis.
Descriptive analysis is the simplest and most common use of data in businesses today, because it answers the “what happened” type of questions by summarizing past data, usually in the form of dashboards. It analyses a complete data or sample of summarized numerical data and shows the mean and deviation for continuous data – percentage and frequency for categorical data.
A major function of descriptive analysis in business is to track Key Performance Indicators (KPIs) which describes how a business is performing based on chosen benchmarks.
Business applications of descriptive analysis include:
- KPI dashboards
- Monthly revenue reports
- Sales leads overview
Inferential analysis analyses data samples from complete data. With inferential Analysis, it becomes possible to find different conclusions from the same data, simply by selecting different samples.
While descriptive analysis shows what happened, Diagnostic Analysis tries to know “Why it happened” by finding the cause based on the insight found from descriptive analytics and then narrows it down to find the causes of those outcomes.
Also referred to as root cause analysis, with processes like data discovery, mining and drill down, diagnostic analysis is a step further to statistical analysis to provide more in-depth information to answer the questions.
A major function of this type of analysis is to identify behavior patterns of data.
If you encounter a new problem in your business process, this Analysis helps you find similar patterns of that problem and may have chances to use similar prescriptions for the new problems.
Business applications of diagnostic analysis include:
- A freight company investigating the cause of slow shipments in a certain region
- A SaaS company drilling down to determine which marketing activities increased trials
Predictive analysis is used to make predictions based on current or past data. It uses the data summarized from descriptive and diagnostic analyses to make logical predictions of the outcomes of events to know what is likely to happen.
With predictive analysis, it become important to note that forecasting is only an estimate; the accuracy of predictions depends on a quality and detailed data.
Business applications of predictive analysis include:
- Risk Assessment and fraud detection
- Sales Forecasting and Marketing Campaigns optimization
- Using customer segmentation to determine which leads have the best chance of converting
- Operations Improvement: Forecasting inventory and managing resources helps improve business operations. For example, airlines use predictive analysis to set ticket prices.
Prescriptive Analysis combines the insight from descriptive, diagnostic and predictive analysis accordingly to determine what line of action to take to either solve a current problem or make a strategic business decision. It emphasizes more on actionable insights instead of data monitoring.
While descriptive analytics aims to provide insight into what has happened, Diagnostic analytics to explain why it happened and predictive analytics helps model and forecast what might happen, prescriptive analytics aims to determine the proper solution or outcome among various choices, since the parameters are known.
A perfect example of prescriptive analytics is the Artificial intelligence (AI), since the AI systems consumes a large amount of data for continuous learning and then use the information, data or pattern learned to make informed decisions. Currently, most of the big data-driven companies (Apple, Facebook, Netflix, etc.) are utilizing prescriptive analytics and AI to improve decision making.
Further Readings on ITTVIS