"A graph presents a limited number of figures in a bold and forceful manner. To do this it usually must omit a large number of figures available on the subject. The choice of what graphic format to use is largely a matter of deciding what figures have the greatest significance to the intended reader and what figures he can best afford to skip." (Peter H Selby, "Interpreting Graphs and Tables", 1976)
"Any graphic format can be executed well, or poorly, for a particular purpose. This is often a more significant variable than the choice of format." (Macdonald-Ross, 1977)
"The main benefit of tabular presentation is its compactness; a great deal of data can be put on a single page. Also, even with the two-digit restriction a table presents numbers more exactly than bar or pie charts do. Therefore it seems likely that tables will remain the preferred format for professional users. The great weakness of tables is their abstract nature. A table consists entirely of abstract symbols-words and numbers." (Michael Macdonald-Ross, "Graphics in Texts", Review of Research in Education Vol. 5, 1977)
"Some believe that the vertical bar should be used when comparing similar items for different time periods and the horizontal bar for comparing different items for the same time period. However, most people find the vertical-bar format easier to prepare and read. and a more effective way to show most types of comparisons." (Robert Lefferts, "Elements of Graphics: How to prepare charts and graphs for effective reports", 1981)
"Charts are used to represent quantitative data in a graphic format. A chart visually illustrates relationships between numbers. When creating a chart, keep in mind that the goal is to represent the data in a simplified and appealing way so as not to muddle the message the chart is meant to convey." (Dennis K Lieu & Sheryl Sorby, "Visualization, Modeling, and Graphics for Engineering Design", 2009)
"For a visual to qualify as beautiful, it must be aesthetically pleasing, yes, but it must also be novel, informative, and efficient. [...] For a visual to truly be beautiful, it must go beyond merely being a conduit for information and offer some novelty: a fresh look at the data or a format that gives readers a spark of excitement and results in a new level of understanding. Well-understood formats (e.g., scatterplots) may be accessible and effective, but for the most part they no longer have the ability to surprise or delight us. Most often, designs that delight us do so not because they were designed to be novel, but because they were designed to be effective; their novelty is a byproduct of effectively revealing some new insight about the world." (Noah Iliinsky, "On Beauty", [in "Beautiful Visualization"] 2010)
"The first requirement of a beautiful visualization is that it is novel, fresh, or unique. It is difficult (though not impossible) to achieve the necessary novelty using default formats. In most situations, well-defined formats have well-defined, rational conventions of use: line graphs for continuous data, bar graphs for discrete data, pie graphs for when you are more interested in a pretty picture than conveying knowledge." (Noah Iliinsky, "On Beauty", [in "Beautiful Visualization"] 2010)
"The best visualizations will reveal what is interesting about the specific data set you’re working with. Different data may require different approaches, encodings, or techniques to reveal its interesting aspects. While default visualization formats are a great place to start, and may come with the correct design choices pre-selected, sometimes the data will yield new knowledge when a different visualization approach or format is used." (Noah Iliinsky & Julie Steel, "Designing Data Visualizations", 2011)
"Infographics combine data with design to enable visual learning. This communication process helps deliver complex information in a way that is more quickly and easily understood. [...] In an era of data overload, infographics offer your audience information in a format that is easy to consume and share. [...] A well-placed, self-contained infographic addresses our need to be confident about the content we’re sharing. Infographics relay the gist of your information quickly, increasing the chance for it to be shared and fueling its spread across a wide variety of digital channels." (Mark Smiciklas, "The Power of Infographics: Using Pictures to Communicate and Connect with Your Audiences", 2012)
"Presenting data in a graphical format makes it much easier to see and understand what is happening with the data. Data visualization applies to all phases of the data science process." (John D Kelleher & Brendan Tierney, "Data Science", 2018)
"There is often no one 'best' visualization, because it depends on context, what your audience already knows, how numerate or scientifically trained they are, what formats and conventions are regarded as standard in the particular field you’re working in, the medium you can use, and so on. It’s also partly scientific and partly artistic, so you get to express your own design style in it, which is what makes it so fascinating." (Robert Grant, "Data Visualization: Charts, Maps and Interactive Graphics", 2019)
"Data is dirty. Let's just get that out there. How is it dirty? In all sorts of ways. Misspelled text values, date format problems, mismatching units, missing values, null values, incompatible geospatial coordinate formats, the list goes on and on." (Ben Jones, "Avoiding Data Pitfalls: How to Steer Clear of Common Blunders When Working with Data and Presenting Analysis and Visualizations", 2020)
