3 Building Blocks of the Language of Data

Hiring managers say that one of the hardest skillsets to find in an employee or candidate is the ability to understand and communicate with data. Discussions around data are becoming an essential part of our personal and professional lives - yet most of us struggle with this.

These data-focused conversations move a company forward by going beyond the basic “what is it” and getting to “what does this mean and what can we do”. Ultimately, the goal of data is to foster better business decisions. To be able to speak the language of data, you’ll need to begin by knowing the structure - the essential building blocks - of data and how they work together.

Understand the components of data

Let’s take an everyday example: you are helping your son or daughter look for the right college. You want to help them make the best choice possible, yet there are so many factors to consider. Good thing publishers like US News & World Report have put together data products to help you wade through the pool of information.  

Using our college search scenario, we’ll illustrate the basic building blocks of charts, tables and other data visuals.

1. Elements: The person, place or object doing something. When you are checking out one of the college lists like National University Rankings, the name of the university represents an element. You can also think of it when looking at a table of data (see below), where each row of information represents an element -- in this case, Princeton or Harvard.

2. Dimensions: These describe characteristics of the elements involved. Dimensions are details which you can use to understand the story about the element. Dimensions can help you narrow down your list with filtering and can be found in the columns of a table. A dimension you might use to filter by when looking for colleges would be location - which state a college is in.

3. Metrics: Metrics answer questions like how much or how many? Metrics are easy to see because they are objects and/or actions analyzed in a mathematical expression such as the sum or average. So in your college search you may want to know the graduation or freshmen retention rate. The metrics can also be found in the columns of the data table.

 

Most of the time when we interact with data it’s already summarized, such as the Top 10 Colleges. The analyst has grouped certain dimensions together and highlighted metrics to help the us find the right schools.

Use the data building blocks to review tables and charts

Take a minute to visualize these building blocks coming together, each serving a role in the explanation of the data story. Each row in the data table tells a story about the element. The dimensions and metrics are characteristics of the element. You can filter by dimension, summarize by adding up or taking an average of the metrics, or break elements out by dimensions for comparisons.

Now when you look at the data table above you see the story told about each school. This helps frame what the data is about and how to compare it. The element gives you the individual perspective and the columns give the bigger picture. As you take control of the data table, remember you can remove the columns that aren’t helpful to allow you to focus on those that are useful. For example, you might be looking at schools under 45k tuition with less than 10k students enrolled. This narrows your results to a single element, or school, Princeton it is!


Congratulations, you now have the data building blocks ready to construct a new pathway of interpreting data. As a next step, we will dive into gaining insight from the data and visualizations as well as the different questions to keep in mind when analyzing information.

Find out more on effective data visualization from our book, Data Fluency. …. and make data more delicious for everyone.

Excerpted with permission from the publisher, Wiley, from Data Fluency: Empowering Your Organization with Effective Data Communication by Zach Gemignani, Chris Gemignani, Richard Galentino, Patrick Schuermann.  Copyright © 2014.