Understanding Open Access Data Using Visualizations in R

BACKGROUND: As access to open data is increasing, researchers gain the opportunity to build integrated data sets and to conduct more powerful statistical analyses. However, using open access data presents challenges for researchers in understanding the data. Visualizations allow researchers to address these challenges by facilitating a greater understanding of the information available. AIMS: This paper illustrates how visuals can address the challenges that researchers face when using open access data, such as: (1) becoming familiar with the data, (2) identifying patterns and trends within the data, and (3) determining how to integrate data from multiple studies. DATA: This paper uses data from an integrative data analysis study that combines data from four prospective studies of children’s responses to natural disasters including Hurricane Andrew, Hurricane Charley, Hurricane Katrina, and Hurricane Ike. The integrated dataset assessed posttraumatic stress symptoms, hurricane exposure, anxiety, life events, and social support among 1707 participants (53.61% female). The children’s ages ranged from 7 to 16 years (mean = 9.61, SD = 1.60). CONCLUSIONS: Visualizations serve as an effective method of understanding new and unfamiliar data sets. In response to the growth of open access data, researchers must develop the skills necessary to create informative visuals. Most research-based graduate programs do not require programming-based courses for graduation. More opportunities for training in programming languages need to be offered so that future researchers are better prepared to understand new data. This paper discusses implications of current graduate course requirements and standard journal practices on how researchers visualize data.