I always hear about Type I and Type II errors in business and how important it is that consultants understand these concepts. Why should I care about this?
People are referring to a statistical concept where a Type I error is a false positive and Type II error is a false negative. For the statistician, a Type I error is rejecting the null hypothesis when it should have been accepted. For a businessperson or consultant, a Type I error is seeing something that is not really there. Type II errors are missing something that is really there (and potentially company making or breaking).
A Type II error (false negative) can be serious when looking at competitive markets or human resource issues such as culture or employee opinions. Inadequate surveys or incomplete analysis may lead a consultant to conclude that there are not serious competitors or impending revolts among employees when, in fact, there are. Depending on the situation, a Type II error may result in serious losses for a company or put it out of business.
False positives are of most interest to consultants engaging in diagnostic or investigative activities, in two ways. As a consultant whose job it is to find problems to solve or opportunities to capture, we are looking for something on which to act. Maybe a process is "broken" or a market is "large and available" to your client. In either case, you may identify something that is not really significant enough to expend resources on. Alternatively, as a result of your activities, you conclude that your impact is significant when it really is not. In both cases, you have overstated the significance, or even existence, of your role to the client. Understanding Type I and Type II errors gives you good perspective on your role and significance to a client. Tip:
Think in terms of medical testing when you consider how you are going to control for Type I and Type II errors. The worst outcome when looking for a serious disease is to conclude it is not present when it is (Type II). To accommodate that, we use screening procedures that are relatively fast, cheap and for which we can tolerate a Type I (false positive) error. As a consultant, you may want to develop protocols that let you quickly tease out potential problem areas and for which you recognize there may be Type I errors. Those items that show up may be real or, more likely, false positives. Then you can proceed with more focused and rigorous protocols to look more closely at an issue, recognizing that what you want to avoid is a Type II error (false negative). You don't have to be a statistician to understand the concept and how your ability to mitigate risk on behalf of your client is a significant value added. © 2011 Institute of Management Consultants USA