Data is the food of statistics. Data means any item of information however presented or represented¹. A datum can be an item of text such as a name or an address or a number or numerical expression. A number of related data may be associated together to form a record – each separate data item is then referred to as a field within the record. Many records together form a table or database.

For data to be meaningful and useful the items of data must be gathered or captured and recorded in a systematic manner². This is referred to as data handling. Data handling may be as simple as orderly recording on a sheet of paper or the completion of entry forms on a computer screen. Data integrity means putting data in its proper format in its proper place. Data accuracy means that every element of the data is correct whether it be the spelling of a text item, a digit in a number or the proper position of the decimal place within a number. Data validation is a system of checking that the item of data is consistent and meaningful. Accuracy, integrity and validation are essential to proper data handling.

Modern computers allow us to store zillions of items of data and records with relative ease. In itself, such stored data is useless unless we can present it³. There are numerous ways of presenting data from the simplest list, to ordered tables to graphical outputs such as charts which can take many forms. In presenting data we should seek the methods that most clearly communicate the meaning and are most easily readable. Readily available software programs offer numerous options for data presentation. The art of data presentation is choosing from the many to achieve clarity and to avoid the temptation to be excessively clever or flamboyant.

Some data may effectively be presented with little or no manipulation; others only make sense if the data have first been subjected to one or more forms of analysis. The information implicit in some data is obvious; for others, the data must be “mined” – one has to dig into the data and analyze it using more or less sophisticated mathematical (statistical) techniques for its meaning to become apparent. The data interpretation and analysis is what converts data to information and justifies the effort and time spent in data handling⁴.

References:

1. Secic M, Lang T, eds. How to Report Statistics in Medicine: Annotated Guidelines for Authors, Editors, and Reviewers. second.; 2006. https://www.amazon.com/How-Report-Statistics-Medicine-Guidelines/dp/1930513690. Accessed February 17, 2021.
2. Riffenburgh R. Statistics in Medicine – 3rd Edition. https://www.elsevier.com/books/statistics-in-medicine/riffenburgh/978-0-12-384864-2. Published 2012. Accessed February 17, 2021.
3. Nussbaumer Knaflic C. Storytelling with Data: A Data Visualization Guide for Business Professionals: Nussbaumer Knaflic, Cole: 9781119002253: Amazon.Com: Books.; 2015. https://www.amazon.com/Storytelling-Data-Visualization-Business-Professionals/dp/1119002257/ref=asc_df_1119002257/?tag=hyprod-20&linkCode=df0&hvadid=312118059795&hvpos=&hvnetw=g&hvrand=10253410397677754541&hvpone=&hvptwo=&hvqmt=&hvdev=c&hvdvcmdl=&hvlocint. Accessed February 17, 2021.
4. Jones B. Avoiding Data Pitfalls: How to Steer Clear of Common Blunders When Working with Data and Presenting Analysis and Visualizations. Hoboken, NJ: J Wiley & Sons; 2020. https://www.amazon.com/Avoiding-Data-Pitfalls-presenting-visualizations/dp/1119278163/ref=asc_df_1119278163/?tag=hyprod-20&linkCode=df0&hvadid=385709422286&hvpos=&hvnetw=g&hvrand=10253410397677754541&hvpone=&hvptwo=&hvqmt=&hvdev=c&hvdvcmdl=&hvlocint=&hvlo. Accessed February 17, 2021.