{"id":574,"date":"2025-04-07T12:02:05","date_gmt":"2025-04-07T12:02:05","guid":{"rendered":"https:\/\/pressbooks.palni.org\/leveragingdatavisualizationtocommunicateeffectively\/?post_type=chapter&p=574"},"modified":"2025-07-07T21:35:08","modified_gmt":"2025-07-07T21:35:08","slug":"visualize-data-with-purpose","status":"publish","type":"chapter","link":"https:\/\/pressbooks.palni.org\/leveragingdatavisualizationtocommunicateeffectively\/chapter\/visualize-data-with-purpose\/","title":{"raw":"Visualize Data With Purpose","rendered":"Visualize Data With Purpose"},"content":{"raw":"
\r\n

Stories change people while statistics give them something to argue about.<\/p>\r\n

\u2014Bernie Siegel, author and surgeon<\/p>\r\n<\/blockquote>\r\n

\r\n

What Do You Think?<\/strong><\/p>\r\n

Michelle Goodwin was the president and CEO of a drop-shipping company, named Bridges. The name \u201cBridges\u201d fit since the software bridged a connection between vendor (seller) and buyer through their manufacturing plants. The company\u2019s success hinged on her software app, but each new medium added to the catalog brought its own set of problems to the code. The company was expanding rapidly into various markets including jewelry, blankets, and acrylic and the manufacturing plants could provide any of the customized options and ship it out within 48 hours.<\/p>\r\n

Michelle was at her limit. She understood coding but interpreting financial statements, financial reports, or general manufacturing reports now took up 80% of her time. She wanted to spend her time dreaming up the next medium for the catalog, not sifting through reports or asking questions that led to asking another and another. Each question left her feeling as if her executive team expected her to know the answer.<\/p>\r\n

She cringed when she recalled her outburst at the last executive meeting. But could they blame her when the finance executive Thomas Perry announced a $40,000 penalty for late payments on the VAT? And what was VAT anyway?<\/p>\r\n

Although the penalty was eventually waived, Michelle asked Thomas to discover how this happened. Thomas quickly answered, \u201cI can tell you exactly why it happened. We have such a high turnover rate in my department; I\u2019ve been using contract help. When we expanded our sales into Europe, none of my contractors had experience or even knew this was a \u2018Europe\u2019 thing. This value-added tax (VAT) is assessed at each production stage, and we just didn\u2019t know about it.\u201d<\/p>\r\n

Michelle was good at reading body language and tried to keep her tone calm and friendly. She could tell that Thomas blamed himself for the problem. Michelle leaned in and placed her elbows on the table, \u201cThomas, I didn\u2019t know your department was so shorthanded. What can we do to fix this and more importantly, how can we develop a reporting setup that alerts me to staffing issues?\u201d<\/p>\r\n

Michelle picked up the coffeepot and topped her cup, asking, \u201cMore coffee, Thomas?\u201d Michelle could see that Thomas was giving this some thought. \u201cMichelle, I\u2019ve been giving you mostly raw reports with some graphs on the financial information. What if we brainstorm with the other executives and find out what issues should \u2018hit\u2019 our weekly reports?\u201d<\/p>\r\n

Michelle smiled, \u201cGo on\u2014what else?\u201d<\/p>\r\n

Thomas hesitated, \u201cI know the manufacturing reports come in daily to you. Are you aware that the shipping is delayed, and most items aren\u2019t shipped within the 24-hour guideline?\u201d<\/p>\r\n

\u201cWhat? How is that possible?\u201d Michelle squeaked and reached for the 25-page report and flipped to the last page. She knew the shipping data in hours was summarized there. As she examined it thoroughly, she realized it had the data of only one of the plants, and not all three.<\/p>\r\n

Michelle could feel her face growing hot, but looked directly at Thomas, \u201cIt\u2019s clear that we are growing so fast that we need to consider how we give proper oversight and make good decisions.\u201d<\/p>\r\n

\u201cI agree, Michelle. We need to visualize the data with purpose and figure out a way to manage and not become overwhelmed. I think we almost need a retreat, but I don\u2019t think we have time!\u201d<\/p>\r\n

Michelle laughed, \u201cLet\u2019s keep our retreats for the team-building events. How about we look through our current reports and see what has purpose and what is missing.\u201d<\/p>\r\n

Thomas, showing some excitement, turned his laptop so they could both see it, \u201cI\u2019ve been looking at a KPI dashboard in my own area. What if we modified your dashboard to the key pieces of information you need?\u201d<\/p>\r\n

Michelle started laughing, \u201cThis is why you were hired, Thomas\u2014you have a knack for anticipating what I need. I think I needed the threat of a $40k penalty to make me realize the importance of purpose<\/strong>!\u201d<\/p>\r\n\r\n<\/div>\r\n

Introduction<\/h1>\r\n

In the realm of data analysis, the ability to transform raw data into meaningful insights is a skill that sets apart the adept from the novice. In this chapter, we look at visualizing data with purpose<\/strong>, recognizing that the manner in which information is presented can profoundly influence our understanding of complex datasets. Effective data visualization goes beyond creating aesthetically pleasing charts; it is a strategic process that aligns with the specific nature and objective of the data at hand.<\/p>\r\n

We already know the power of visualizations. For example, illustrations are 83% more effective than text for long-term memory and a study by the University of Minnesota indicated that the human brain processes visual information 60,000 times faster than text (Verma, 2023, para. 5, 7). The symbiotic relationship between data types and visualization techniques emphasizes the importance of tailoring visualization to the inherent characteristics of the dataset. Essentially, a line chart may not reveal the same insight as a bar chart. Or even worse\u2014the presenter tries to show everything, and insight is lost in the clutter.<\/p>\r\n

This chapter also looks at qualitative data visualizations and the pivotal role in uncovering patterns and trends from an academic setting. In previous chapters, the authors demonstrated outliers and correlations. This chapter looks at guidelines and standards, particularly those engaged in academic pursuits such as writing theses and dissertations, and how the APA 7th<\/sup> edition style guide is used. The chapter will cover best practices for incorporating visualizations into scholarly works, ensuring that the clarity and integrity of the data are preserved while meeting the stringent requirements of academic standards.<\/p>\r\n

Purpose<\/strong> should drive the use of key performance indicators (KPI) for dashboards to provide a snapshot of the way things are now. An example of an operational KPI dashboard might be tracking severe weather and accidents to help local governments assign utility vehicles and first responders. In a corporate setting, KPIs should align with the organizational objectives and can include sales targets, production output, shipping goals, and more nonfinancial data like customer satisfaction scores, or employee turnover and\/or overtime hours. And KPIs that are aligned with other frameworks like a Balanced Scorecard approach can be powerful in reaching strategic objectives.<\/p>\r\n

This chapter serves as a comprehensive guide for anyone seeking to visualize data with purpose. Aligning visualization techniques with data types, unraveling qualitative intricacies, aligning strategies and KPIs, or navigating academic reporting, require a presenter to use the tools necessary to extract meaningful insight.<\/p>\r\n

Chapter 6 addresses the following learning objectives.<\/p>\r\n\r\n

\r\n

Learning Objectives<\/p>\r\n\r\n<\/header>\r\n

\r\n

At the end of this chapter, students should be able to:<\/p>\r\n\r\n

    \r\n \t
  1. LO 1: Choose the appropriate infographic and chart based on data type.<\/li>\r\n \t
  2. LO 2: Design appropriate visualizations for key performance indicators (KPIs).<\/li>\r\n \t
  3. LO 3: Apply appropriate visualizations that meet academic standards and follow APA 7th<\/sup> edition.<\/li>\r\n<\/ol>\r\n

    Key Terms:<\/em> APA 7th edition, categorical, continuous, data type, discrete, interval scales, key performance indicators (KPIs), nominal, normally distributed, ordinal, parametric test, Qlik, Qlik Sense, ratio scales, SMART goals, scale, skewed data, variables<\/p>\r\nDownload Chapter 6 PowerPoint (8 MB)<\/a>\r\nDownload Chapter 6 Student Files (<1 MB).<\/a>\r\n\r\n<\/div>\r\n<\/div>\r\n

    6.1 Best Graphical Visualizations Based on Data Type and Purpose<\/h1>\r\n
    \r\n

    Often the most effective way to describe, explore, and summarize a set of numbers\u2014even a very large set\u2014is to look at pictures of those numbers.<\/p>\r\n

    \u2014Edward Tufte, The Visual Display of Quantitative Information<\/em><\/p>\r\n<\/blockquote>\r\n

    Understanding your data type will help you choose a suitable graph or infographic, but understanding your purpose in conjunction with the data type helps you reach your audience and present your insights.<\/p>\r\n

    In any setting (but especially an academic setting), understanding your data types will help you choose a suitable summary statistic and analysis, and the best graph or data visualization. In an academic setting, students tend to leap to hypothesis testing. In a corporate setting, the typical KPIs are used, when it might be better to investigate the data with summary statistics and summary charts. Get in the habit of sorting your data with filters to determine issues like outliers, missing data, and trends. Use quick summary and aggregations like SUM, AVERAGE, and COUNT. With the growing application of artificial intelligence, upload data and ask the AI \u201cWhat does this data tell me?\u201d Remember, charts don\u2019t need to be in statistical software (although they can). You can create most of the charts in Excel or a more advanced Power BI.<\/p>\r\n

    Perhaps you have seen these terms in an undergraduate statistics course, but how many of these types of data can you explain as listed in Exhibit 6.1?<\/p>\r\nExhibit 6.1\u2014Types of Data<\/strong>\r\n\r\n[caption id=\"attachment_1479\" align=\"alignnone\" width=\"1024\"]\"an Note: Author Illustration (2025)[\/caption]\r\n

    In the realm of data analysis, understanding the two primary types plays a crucial role: scale and categorical data. Scale data are also known as quantitative or numerical data whereas categorical data are often termed qualitative or nominal data representing distinct categories without inherent numerical significance. Scales can be either continuous or discrete and the types of summary statistics will depend on if the data are normally distributed or skewed. For categorical data type, you look at either ordinal or nominal. Make sure to look at the examples with each data type.<\/p>\r\n

    Now look at the ways to describe and visualize the data when we have nominal data, ordinal data, interval data, and ratio data.<\/p>\r\n

    Nominal scale<\/strong> describes the variable with categories. \u201cIf you were to assign a numerical value to a category; a higher score would not necessarily mean that there was more of some quality\u201d (Adams & McGuire, 2022, p. 66)<\/p>\r\n

    Examples of nominal variables:<\/em><\/span> zip code, eye color, political party, gender.<\/p>\r\n\r\n