Lean Six Sigma and Calorie-Controlled Big Data?

By John Morgan, Martin Brenig-Jones

There seems to be a lot of talk about big data and the importance of turning it into smart data. And, there’s a lot of available data. Google claims that every two days people create as much information as they did from the beginning of time until 2003. Given the number of emails most people receive, Google is probably right. As always, there’s also a lot of talk about slimming and reducing calories.

Big data starts with little data, whether it’s smart or not. Focusing on process data, for a moment, many organisations seem to have data coming out of their ears — lots of small data from different processes that builds into big data within the organisation. Unfortunately, that data isn’t always the right data. Sometimes organisations measure things because they can measure them – but those things aren’t necessarily the right things to be measured and the resulting data doesn’t help you manage your organisation and its processes.

You probably know that choosing what to measure and how to present your data are important activities. But so too is deciding what not to measure. Lean Six Sigma requires you to manage by fact and have good data – but that doesn’t mean you need more data than you currently produce. It means you have the right data. You need to review the data you currently have and decide whether it really is helping you manage your processes. Does the data add value or is it a waste? Is it really being used?

You need to be measuring the right things, but you also need to make sure that you’re collecting the data through an effective and efficient data collection process. Sometimes data isn’t accurate — intentionally or not — and even if the data is accurate, it may be presented in a way that makes interpretation difficult. Managers often present data as a page full of numbers to encourage comparisons with last week’s results or even the results for this week last year. This situation is compounded further if the results show only averages or percentages and you can’t understand the range of performance or the variation in your process performance. The net result is a lot of jumping to conclusions through assumptions that, at best, are misguided.

So, you need the right data, collected in the right way, presented appropriately and interpreted correctly. That way the data becomes smart and you can manage by fact. Interpreting data correctly is vital; it’s an area where control charts can help enormously, though they won’t always be the right data display tool.

Misinterpreting data isn’t new, of course, and returning to the calorie reference, did you know how calorie counts were determined? Conventional wisdom dictates that wine seems to have a pretty high calorie count. But should it? Is the interpretation of the data that resulted in this assessment correct?

Back in the 1880s, an American chemist, Wilbur Atwater, looked to measure the energy in different foods and drink. Essentially, he burnt them in a furnace and measured the heat that they produced. These units of energy became known as calories. Now, when he burned alcohol, it flared up very quickly, of course, producing a lot of heat and earning wine a high calorie count. But given that alcohol is certain to burn quickly, did he interpret the data correctly? Well, a small but growing number of nutritionists aren’t so sure. They feel the calorie theory is flawed and should perhaps be replaced by something known as the Glycemic Index. No doubt the conclusions to this will come in due course!

Closer to the workplace, it’s likely that some of the interpretations that some managers make about the process data they see is definitely flawed. All managers need to better understand how to collect, present, and interpret data more effectively. When they do, they’ll find that from little data, big data grows, but they need to make sure it’s smart. Hopefully, you can drink to that!