From the course: Everyday Statistics, with Eddie Davila

Modern organizations use statistics

From the course: Everyday Statistics, with Eddie Davila

Start my 1-month free trial Buy for my team

Modern organizations use statistics

“

- [Instructor] Analytics, a word that seems to be used everywhere, and modern organizations seem to love the idea of analytics, learning from numbers in an effort to see the future. So organizations go out and invest in costly analytics tools and they hire high-priced and in-demand analytics professionals. The organizations' intentions are good. Using data to learn from the past, understand the present, and predict the future. In a world filled with data, this all makes sense. Unfortunately, too many companies don't get the results they were expecting when they made those expensive investments in tools and when they hired those analytics professionals. In many cases, these organizations are putting the cart before the horse. Giving an unprepared company a high-powered analytics arsenal is about as useful as giving someone like me full access to a home improvement store. You can give me all the tools and equipment in the world, but it doesn't mean I'll be able to build a house, or even a chair. And I probably won't be very effective at fixing things, either. To build something new, I need to know what I want to build. And I need to learn how to build it. And if I own a home that needs repairs, without knowledge of how to use the tools and how to make the repairs, the home improvement store isn't much help. To maximize the value of their analytics teams and their analytics tools, organizations need to start by answering some simple questions. First, an organization needs to ask a specific question. Data doesn't know what's important to you. It can't magically give you something profound. You need to ask a specific question. For example, what's the weather going to be on November 1st in Paris? Who will win the next World Cup? What will the population of the United States be in the year 2050? Now that you have your very specific question, outline what would be a convincing answer. Telling the future is an imperfect science, so giving exact answers is rarely possible. If you want to know the likely temperature in Paris on November 1st, begin to think about which statistics would lead to a reliable answer. Finally, you need data. Not all data sources are reliable. Not all data sets provide complete data. Find the best data available for this job. Now, using the best data sets available and using your statistical foundation, you can begin to construct a statistical answer to the specific question. One other very important thing to consider. You don't hire a plumber to do your electrical work. Your analytics team has to have some knowledge that will be useful in answering the question. As your organization seeks to maximize the power of analytics, be sure you have the right people, the right data, and the right tools to answer your very specific questions.

Contents