As I’ve progressed through the Business Statistics Specialization on Coursera, one of the things that I’ve noted, and been grateful for, is that you don’t need to fully understand the maths of statistical methods to use them. The main thing you need to know and be able to us, are Excel functions.
There are Excel functions for standard deviation, normal distribution, correlation and t-distributions, to name a few. There is also the analysis toolpak addin (installed by default but needs to be enabled) that will automatically show you all of that data and more for a linear regression of a set of data.
Excel allows someone who barely understands the maths to make very good predictions when they have the right data in front of them. That coupled with the data aggregation and transformation powers of PowerQuery and PowerPivot in Excel significantly lowers the barrier to entry into Business Analytics.
My favourite part about this is that almost all of this is new to me. Last year I knew of the Analysis Toolpak, I knew of PowerPivot, I knew of the distribution functions in Excel. What I didn’t know was how, when or why I would use them. This year, over just a few months, I’ve discovered and started becoming comfortable with all of these things. Even though I am still developing Excel skills (which I did not think would be happening this year!), they are completely different Excel skills to what is traditionally used.
There are only two more days between me and that Predictive Analytics Nanodegree, and one of the prerequisites is Excel knowledge. How much more Excel is there left to learn? Only time will tell.