Let’s start with the skill that is in the very name of People Analytics, analytics.

For some, the analytics part is the intimidating part. This is especially true for those who don’t have a deep background or education in analytics topics. There’s a common misconception that you have to be “good at math” or that learning analytics later in your career is too difficult. Let me tell you right now, neither of those things is true.

I have a confession. I’m actually quite terrible at basic math – please don’t ask me to add numbers together quickly or multiply anything by 8! I almost failed statistics the first time I attempted it. Yet, I ended up falling in love with it and having a very fulfilling career in People Analytics. I even teach statistics now! For me, none of the numbers or calculations ever made sense or stuck in my memory until I needed them at work and saw what I could do with them. Once I stopped trying to memorize calculations and focused on learning which types of analytics were good for answering which kinds of questions, things started to ‘click’ in ways they never had before.

I now like to think of doing analytics like baking. I think of doing the “math” parts like using appliances in a kitchen (the blender, mixer, oven, etc). Knowing the internal mechanics of these appliances isn’t essential, but understanding their functions and how to operate them safely is crucial. You don’t need to know how the oven was built or even how exactly it works. But, if you want to bake a cake, you should at least know that the oven is a better choice than the toaster. And, you need to learn how to use it and set the right temperature and time for baking. Similarly, analytical approaches allow you to “cook up” insights from data. If you want to have your People Analytics cake and eat it too, you don’t need a deep math or statistics background to start. But you will need enough knowledge of which “appliances” are available and appropriate for your purposes and an understanding of when and how to use them appropriately. You can choose to go deep with your learning and become a master chef, or stick to the basics and follow recipes with detailed instructions. If you are excited about People Analytics but unsure whether you have enough “math” skills to start, I’m here to tell you that you do. As long as you are willing to learn and build the skills.

Who knows, you may learn that you love those “math” parts more than you realized once you get to know them from a new vantage point. For me, I eventually learned to appreciate those crazy underlying math calculations. But that happened only after, and only because, I understood the outcomes. Starting with the goal in mind was what allowed me to understand the steps in the calculations that were designed to get me there.

Quantitative Analytics

Analytics ≠ Analysis of Numbers

According to the Oxford Dictionary, to “analyze” is to examine methodically and in detail the constitution or structure of something (especially information), typically for purposes of explanation and interpretation. Notice that this definition doesn’t mention numbers. Analysis can be performed on any kind of information. When people hear analysis, the analysis of quantitative data usually comes to mind. Quantitative data is all about numbers and measurements. It allows you to count or quantify things, like the number of employees in a company, their salaries, or their performance scores. But, qualitative data is just as critical and some might argue more so in People Analytics where the feelings, experiences, and context in which work happens are critical. Qualitative data uses words and observations to capture things like employee sentiment, job satisfaction, or reasons for leaving a company. Both quantitative and qualitative data play a crucial role in understanding a situation; they provide different but valuable perspectives.

Analytics involves identifying summarizations, patterns, or trends within data. Once relationships or connections have been identified, they can be used to make informed decisions, improve processes, or predict future outcomes. With so many uses, it can be helpful to think of analytics in the categories of descriptive, diagnostic, predictive, and prescriptive analytics – terms that describe the purpose or use of analytics. Descriptive analytics tells the story of what happened (e.g., How many employees left the company? How engaged are employees?). Diagnostic analytics helps us understand the “why” behind those trends (e.g., Why did employees leave? What aspects are related to employee satisfaction?). Predictive analytics peers into the future to anticipate potential outcomes (e.g., How many employees might leave this year? How might we increase employee satisfaction if we improve a given aspect?). Prescriptive analytics recommends the best course of action based on insights (e.g., Attrition may be reduced by up to 10% if you offer a retention bonus of X amount. A targeted engagement program may increase engagement scores by X%).

• Descriptive analytics describes what happened.
• Diagnostic analytics aims to diagnose why it happened.
• Predictive analytics attempt to predict what might happen.
• And, prescriptive analytics attempt to prescribe the best action to take.

Descriptive, diagnostic, predictive, and prescriptive analytics questions can be asked and answered with both quantitative and qualitative data. However, the skills and techniques you will use to answer them are quite different for these two very different types of data. We will discuss both types in this chapter, but let’s start with quantitative analytical skills.