A few years ago a client asked me to help one of his Lean Six Sigma Black Belts who was struggling with data analysis. My first step was to evaluate his data to gain a better understanding of what he was trying to learn from it. To do this I asked him to email me the data files. This was the first red flag; he was unable to email the data because the file size was too large. Before exploring other options to get the data in my hands, I asked him a simple question. “Tell me what you are trying to learn from the data?” His response was, “Once I run a few analysis tools I presume the data will be able to tell me a story, and then I can figure out what I want from it”. Knowing he was lacking a clear goal I asked, “What has the data told you so far?” He responded, “Nothing, I have so much data that when I try to run analysis, it crashes my software, this is where I am stuck.”
Often when analyzing data, we are led to believe that if we have lots of data it will tell us a story. Unfortunately, this is the wrong approach to data analysis, data does not talk on its own. Good data analysis starts with asking great questions, then collecting the data that will help you answer these questions. If you bypass the question generation step, then your data is just a bunch of numbers and characters with very little meaning. The next time you are analyzing information, ask yourself “What do I want to learn from it?” Taking this extra step will save you a lot of time and energy, and will ultimately lead to better data analysis.