P.Mean: If you knew that failure was not an option, what would you do (created 2010-10-01).

There is a question and answer forum on LinkedIn where people ask all sorts of questions. A common theme among some people there is to ask motivational questions, which I try to respond to sometimes with an off-beat answer. There was a question along these lines: "If you knew that failure was not an option, what would you do?" I started off with a rather flippant answer, but then realized that there was a more serious answer.

Here's my first response. If failure is not an option, then any option I choose has to be a successful option. So I choose eating a triple chocolate brownie.

Here's the more serious answer that I posted a day later. Failure is always an option. Statisticians know this and they attach terms to failure such as Type I error (false positive finding) and Type II error (false negative finding). When someone tells you that failure is not an option, what they are saying is that one of the above errors is very costly. You have to conduct your research in such a way that the probability of that type of error is small. It's never zero and shouldn't be because the cost of the other type of error has to be accounted for also, as well as the cost of running your experiment.

If you cannot run an experiment within the resources available to you in such a way as to control the expected cost of "failure" then the proper answer is to not run the experiment.

That's true in more general settings that just research, of course. If failure is "not an option" find out what the true cost of failure is (you getting fired? the company declaring bankruptcy?) and then make choices like an insurance company might, controlling the expected cost (cost of failure times probability of failure). If you can't control the expected cost at a manageable level, then don't start the project.

The other thing to keep in mind is that people who embark on a project while fearful of the results should failure occur will either be very timid or they will try to "game" the system. Neither is a desirable outcome. So if your boss routinely tells you that failure is not an option, find a new boss.

Creative Commons License This work is licensed under a Creative Commons Attribution 3.0 United States License. This page was written by Steve Simon and was last modified on 2010-10-01. Need more information? I have a page with general help resources. You can also browse for pages similar to this one at Category: Hypothesis testing.