Data visualization is an umbrella term referring to the representation of raw data content in a graphic or pictorial manner. Related concepts include information visualization and scientific visualization. Using visual features of encoded data such as position, size, shape, hue and saturation, motion, etc., data visualization applies tools and techniques to communicate the raw data in visual form.
Common examples include charts, graphs, timelines, maps, and even tables.
Raw data and statistics can often appear confusing. Many research data sets are going to be overwhelming in size. Data visualization applies what we know about human perception to optimize cognition, making it easier to understand, interpret, and analyze patterns, trends, and relationships within the data.
Use of effective data visualization if often focused on one of two primary purposes:
Exploration - sometimes referred to as sense-making or data analysis. Using visualization techniques to examine and discover trends, associations, outliers, etc., that may not be obvious when viewing the raw data.
Explanation - also referred to as storytelling or communication. Creating visualizations that make understanding what the data is saying clearer and more obvious.
Successful data visualization relies on selecting the appropriate tool, technique, and visual expression that most effectively presents the story the data is telling. Data visualization should be considered a means to an end, not an end in itself.
Data visualization is one component of a much broader data analytics life cycle. While there is some variation in defining the full data analytics life cycle, the graphic below presents a general structure encompassing the basic components.
When discussing data visualization, various related terms may be used somewhat loosely. The following is a very brief glossary of commonly used data terminology:
Data Science
Data Analytics
Spatial Analytics
Data cleaning/wrangling/remediation/munging
Data Visualization