Through the Research Commons, students, faculty, and staff can get assistance with:

• Determining the best format to present your data based on research question, data type, audience, and medium
• Creating static, dynamic, and interactive visualizations and infographics
• Identifying appropriate data visualization software for your research project
• Training for a variety of data visualization tools including free and open source options, OSU-licensed resources, and other specialized software, such as Microsoft Excel, Adobe Illustrator, Adobe Photoshop, Adobe InDesign, Tableau, Gephi, Cytoscape, and more.

Data visualization is a way of presenting data in a visual context. Not only can data visualization be used to communicate a large amount of information clearly and concisely, it can help you gain insight into things you would have otherwise been blind to had you only examined the raw data (ex. Ascombe's Quartet).

Because data comes in many forms and is gathered in virtually all disciplines - from population statistics in the U.S. Census, to text analysis of Shakespeare's work, to video recordings of a dance performance - data visualization can also take on various formats. Charts, graphs, timelines, tables, and box-and-whisker-plots are just some of the more recognizable ways to visualize data, but there are many more options out there for you to choose from.

There are three reasons why you should care about data visualization:

1. Big Data - We are living in a world that is increasingly interconnected with devices talking to each other and all generating huge amounts of data be it through social media platforms like Twitter or personal tracking devices like Fitbit. Understanding how to deal with these large datasets and finding meaning from them is a real challenge. Data visualization provides one solution to this problem by helping us make sense of the sheer amount of information, and presenting it in unique and meaningful ways.
2. Information / Data Literacy - Students are expected to be proficient in not only being able to find, read, and understand data, but also create and evaluate visualizations. This is especially important with the increase in "fake news" and other misleading infographics that make it easy for readers to misinterpret data through the guise of fancy graphics. If we’re making decisions, who to vote for, what clothing brands to buy, where to go eat, we need to be able to be smart about data visualization.
3. Fun / Multidisciplinary / Collaborative - What is great about data visualization is that it is applicable in all disciplines and areas of study. Whether you are interested in the sciences, arts, or humanities, there are many opportunities to utilize data visualizations in your own work and research. Visualization offers an avenue for collaboration between disciplines as well, especially with the accessibility and use of programming languages (R, Python, D3.js) with data visualization. 

• Anscombe's Quartet

  

  Property	Value
  Mean of x	9
  Sample variance of x	11
  Mean of y	7.50
  Sample variance of y	4.125
  Correlation between x and y	0.816
  Linear regression line	y = 3 + 0.5x
  Coefficient of determination of the linear regression	0.67

  Anscombe's Quartet is a famous, constructed group of four datasets that demonstrates the importance of visualizing data. While all four of these datasets have similar summary statistics (mean, variance, correlation, etc), they look very different when visualized and plotted in a simple graph. This shows the pitfalls of relying solely on looking at the data and statistics to make observations, and the power of using data visualization in an exploratory way to quickly and easily spot trends, patterns, and outliers.

Visual properties or cues are the different ways we can encode data using things like length, angles, shapes, and hues. William Cleveland and Robert McGill have written about these encodings in their famous paper, Graphical Perception and Graphical Methods for Analyzing Data. As human beings and readers of visualizations, we decode these these visual cues/properties in order to try to understand the meaning behind a particular chart or graph.

One of the key ways we make sure our readers can decode our encodings is to use labels, legends, and keys, depending on the situation.