Merely analyzing the above data on its own is not necessarily enough. Such analysis will give us intermediate technical, statistical findings. However, these lack meaning without further assessment, interpretation and reporting, as discussed next. There are two major subsidiary tasks needed by the successful and well-rounded business analyst.

First among the additional skills is excellent reporting and packaging skills. The consumers of business intelligence and analytics are often non-technical managers, directors, teams, co-workers, or the like. These stakeholders may not be able to digest technical statistical findings, or may not have the time. Your CEO in the above example, for instance, might only give you 5 minutes at an executive or board meeting to discuss your findings. You’ll need to reduce and package them appropriately.

One of your essential tasks is therefore to learn how to package data findings in a way that is most appropriate to the reader. This may require additional skills over and above merely analyzing data, such as graphing, dashboarding, learning to produce HTML or other formatted reports, and many others. Luckily, SAS – the analytics suite this book is based on – has a ”black-belt” in all these skills. See Chapter 9 and Chapter 16 for examples of more intuitive analysis.

This supplementary skill speaks to the ability to interpret statistical results so that they take on greater business meaning, perhaps helping to guide strategy, financial decisions, and the like.

I have a saying for business statistics, which goes something like:

Great business analytics is not about numbers. It is about words: the explanations, interpretations, strategies and decisions that spring from the technical data analyses.

Unfortunately, too many business analytics projects stop at the technical statistical findings, and the analysts lack the skills or confidence to extrapolate the findings further to business implications.

Many data analyses can have varied practical interpretations depending on the way they are presented. Adding a benchmark, as the CEO did a few times earlier in this chapter, immediately makes a statistical finding in context of the benchmark.

This book has a dedicated chapter on extrapolating business analytics to business outcomes, specifically financial outcomes. See Chapter 17 for more on this. Such skills transform average business analysts who can speak “statistics” but cannot speak “business”, into indispensable strategic powerhouses.

Many times, the data gathering and storage in a company is a significant challenge. Data can be from different sources, dispersed around the company or outside the firm, in varied formats, coming in huge volumes or speed, and so on.

Various solutions have been developed to help guide and organize the information architecture of the firm. The well-rounded data analyst will know about and be able to work with various data sources and solutions. The final chapter in this book talks about such issues and skills, including big data, data warehousing, machine learning and algorithms, and others.

Now that you understand the core textbook case, turn to the next chapter for a broad overview of the general statistics process.