Once a company puts Lean Six Sigma strategies and tools to work, they can generate a wealth of data and other information. Project teams conducting deep dives into particular business challenges find themselves armed with plenty of actionable statistical insights.

What comes next is worth focusing attention on. Because a critical component in correctly employing Lean Six Sigma is to understand the risks of making common errors when analyzing data.

Fortunately, Lean Six Sigma accounts for this critical issue. It requires understanding Alpha Risk and Beta Risk. Both measure the risk of teams taking the wrong path in a project improvement project, but in very different ways.

## The Two Common Risks in Data Interpretation

No attempt to use Lean Six Sigma should proceed without team leaders understanding Alpha Risk and Beta Risk, as well as the consequences of each. Much like the null hypothesis, an understanding of these two risks keep teams from making common mistakes.

### Understanding Alpha Risk

Alpha Risk measures the risk of comparing two different sets of data and determining that the differences are significant, when in fact they are not significant. For example, this can occur when a team looks at data from a current operational process and the possible outcome if they changed an aspect of the process. An analysis of the two might show a difference in outcomes, such as less product defects. The team recommends that this single change will provide significantly different outcomes. Executives agree to put the change into action. Then, outcomes do not improve – or may even worsen.

That’s a common mistake. It’s known as a Type I error.

Alpha Risk measures the chance of a Type I error. The primary variable that increases the chance of Alpha Risk is the sample size used in the statistical test or comparison. The smaller the sample size, the higher the Alpha Risk becomes. Conversely, larger sample sizes lower Alpha Risk.

### Examples of Alpha Risk

Small sample sizes plague statistical analysis in everything from sports teams to financial investments. For example, baseball teams may overvalue a hitter who goes on a hot streak, deeming the statistical difference between his stats and those of his fellow players as significant. He’s made a starter, but a month later, he’s back on the bench, his hitting numbers falling.

The same thing can happen to market investors who place too much emphasis on short-term stock movement, then get burned when the stock price falls. In both cases, regression to the mean has occurred. This refers to the statistical phenomenon in which a period of natural variation in repeated data (in these examples, more hits or higher stock prices) are typically followed by measurements closer to the long-term mean.

Alpha Risk also presents itself in medical research. If a new medicine is tested and the condition it treats improves, researchers might conclude that the medicine made the difference. But in just one lab test, other variables could have caused the patient’s improvement. That’s why multiple tests are needed to avoid making a Type I mistake in research.

The best way to avoid Alpha Risk is to increase the size of the statistical sample. Teams then have a better chance of capturing a more representative sample of process outcomes.

### Understanding Beta Risk

Beta Risk measures the chance of a Type II error occurring. This is the direct opposite of a Type I error. With a Type II error, teams dismiss statistical differences as insignificant, when in fact they are very significant. This can also occur when a team analyzes the outcomes of a current process (Process A) with a new approach (Process B). The new approach may, for example, lower the number of product defects. But it might not seem a significant enough change for the team.

If the team decides to continue with Process A even though Process B would improve operational outcomes, they have made a Type II error.

### Example of Beta Risk

Put simply, Beta Risk or Type II error involves deciding that there is no difference between two approaches when, in fact, there is a significant difference. Most of the examples of Beta Risk revolve around another name it is known by: consumer risk.

A Beta Risk in terms of manufacturing might involve a company that produces defective goods because executives believe their current process is better than proposed alternatives, so no change is made. The term “consumer risk” comes from the fact that these defects often impact consumers, who spend money on defective products or services. Automobile manufacturers who have to issue recalls can make a Type II error.

The best method of lowering Beta Risk involves using larger sets of numbers, as with Alpha Risk. In both cases, the longer time period for the data, the better.