Living in an age of information overload, where technology is seamlessly integrated into our lives means we are bombarded with statistics. This can range from data about products that are marketed to us, to the steps we take on our smart watches, to analysing our favourite sport (which is Australia’s favourite past time). It’s likely that you probably see quantitative data routinely at your workplace.
So how do we differentiate the statistics we receive from a simple chart we see on social channels or complex publications?
Here are three principles we use at McCrindle.
- Identify the problem
Before delving into spreadsheets and dashboards, ask yourself: what is this data/report/analytics piece trying to solve? Recognising the problem distils the objective and allows you to focus on what needs to be understood. Optimally, once you have distilled the problem, the other factors should become clear.
- Frame the context
Context plays an important part in understanding analytics. Understanding the history behind your data can distil further insights not on the surface. Context can include several factors and is often the prologue to the way your analysis is built.
For example, time sensitivity can shape the way you understand your data. These common types of quantitative analysis highlight how time plays a factor:
- Descriptive analytics: this is what most people have the greatest exposure to. Think dashboards or reports with data about what happened in the past. Depending on the complexity, these types of reports can almost read for themselves, but are static to a specific point in time. Understanding the context of that point in time helps to fully make sense of the data.
- Predictive analytics: this uses modelling on the past to predict the future. Your report or data often utilises this type of analysis to predict future outcomes based on past results.
- Choose the variables that solve the problem
In a world where everything can be quantified using scalable technology, it can become quite overwhelming! While looking into countless variables can be interesting, it can lead to tangents if they do not follow the objective. Say you want to know what factors are influencing bottlenecks in your call centre help line, you don’t need to look at social media sentiment, for example.
Utilise your analytics team
Finally, it is important to establish a close relationship with your analytics team. You are the expert in the nuances of your business and may be intimidated by all the data. On the other hand, your analytics team know the variables and what to analyse to solve the problem, but they may not fully understand how certain aspects of the business run. A harmonious relationship of open communication to answer each person’s questions transparently and with an aligned understanding of the problem is key to a successful relationship – and can help both parties gain a more holistic picture of the story your data is painting.