It's difficult to imagine conducting research without gathering and analyzing data of some kind - whether that's observations made in a lab, ethnographic field notes, a corpus of texts, or a set of theoretical claims.
Even if we agree that data is extremely important, data is often quite confusing! It's messy, convoluted, hard to conceptualize. You may be unsure the data you have can actually answer the questions you care about. Or alternatively, you may have come up with some promising answers to those questions, but be unclear how to communicate a connection between these claims and the data itself for your readers.
Data visualization is an extremely helpful resource in investigating, analyzing, and communicating research data. The term "data visualization" refers to a collection of techniques that rely on visual perception to communicate data. The "visualization" piece in particular refers to strategies for encoding attributes of data into visual features like position, size, shape, hue and saturation, motion, and so on. When used effectively, data visualization can help a reader grasp a trend or correlation intuitively and near-instantaneously, no matter how massive or complex the underlying data may be.
Data visualization is useful for many research contexts. This guide will emphasize two in particular:
1. Exploratory data analysis - using visualization to explore trends, associations, and outliers in data.
2. Communicating research outcomes - using visualization to express findings observed in data, often after the completion of analysis/experimentation.
Are you new to data visualization? Start with the Introduction: Why Visualize Data?
Would you like to learn more about specific software or a coding library? Start with Tableau, Python and R tools, JavScript tools, and Other tools
Want to build your skills in crafting effective data visualization? Start with Visualization Best Practices and Further Resources