How to ask the right questions?
A Question That Should Concern Every Analyst
Analytics is built on the scientific method. Developing hypotheses is the first step in any form of testing or experimentation. New disciplines like behavioral and cognitive science may be a little less dependent on laboratory testing, but they are still predicated on developing logical and consistent hypotheses. Stated more simply — analysts need to ask the right questions.
Whether you are more of an academic or a pragmatist, the validity, form, and thoughtfulness of the questions you develop will be important to your success. W. Edwards Deming, a man credited with inspiring the Japanese Post-War Miracle, was a statistician and engineer primarily concerned with the development of knowledge and the quality of work. He was equal parts theory and application. He summed up his view on the importance of questions like this:
Knowing How To Ask The Right Question Is Not Easy
Deming wrote several books on the subject. The work of many others could fill a large library. Asking solid questions is both an art and a science. It depends greatly on the outcomes you are trying to obtain and the details of your data and subject matter. Other rules tend to me more generalized and cognitive science provides many warnings for avoiding bias and other logical flaws.
Douglas Adam’s humorously based the creation of the Earth on an attempt at defining the ultimate question. The Hitchhiker’s Guide to the Galaxy tells us that the Earth was a super computer built to determine that question. It’s predecessor was a somewhat less planet-sized computer which had actually already determined the answer… 42. Unfortunately, it was only after that computer completed its work that scientists realized they didn’t really know what the question actually was!
Note — the Hitchhiker’s Trilogy is a great read. The movie is another thing entirely and likely best avoided…
Some Techniques For Forming Solid Questions
Now that you recognize the need for solid question development, consider a few pointers. Frame your questions to provide answers that are meaningful for those who are asking. Don’t rely on them to have been as thoughtful as you are going to be. More here.
Questions that begin with Who, What, Where, and When are better answered by a report than an analyst. If you are spending all your time on questions like these, you are not living a very useful existence. Build them a simple report, it will be more cost effective and much more fulfilling for you. More on that here.
Questions that begin with Why are also a waste of your time. Leave those to philosophers, they will appreciate it. As for your business clients who won’t stop asking, just ask — if I tell you why, what are you going to do with it? The answer will help you craft a question that both of you will be satisfied with.
For more articles on crafting great questions consider:
Analyst Interrogative — Articles On Developing Good Analytic Questions
#1- How to ask a good question
For more from W. Edwards Deming consider:
Analyst Interrogative is a series created by Corsair’s Institute to increase the reader’s understanding of the analytic process. For more articles like these — please subscribe to Comprehension 360.
