Abstract
Graphics are powerful tools to communicate research results and to gain information from data. However, researchers should be careful when deciding which data to plot and the type of graphic to use, as well as other details. The consequence of bad decisions in these features varies from making research results unclear to distortions of these results, through the creation of “chartjunk” with useless information. This paper is not another tutorial about “good graphics” and “bad graphics”. Instead, it presents guidelines for graphic presentation of research results and some uncommon, but useful examples to communicate basic and complex data types, especially multivariate model results, which are commonly presented only by tables. By the end, there are no answers here, just ideas meant to inspire others on how to create their own graphics.
Highlights
Graphical presentations are powerful instruments for the communication of research results
This paper aims to review some important pitfalls when designing and interpreting statistical graphics from research papers
As we reach the end of this paper, you are probably thinking about which graphic to use, after so many examples, and, most importantly, how to do it
Summary
Graphical presentations are powerful instruments for the communication of research results. With these three basic rules, the next tough question to answer is: which graphic model should you choose to present your data? Line and bar plots are some of the most basic and most useful statistical graphics An unusual line plot is presented in figure 4 This graphic describes simulated data from a very common research design where a group is assessed before and after a treatment.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
