Operationally, if you're a baseball GM, then, you look at all the data you can and have to decide how to weigh the idea. If your scout comes in and says "this guy is great in the clutch" you make a decision based on how you assess these things. There are many reasons you might make a decision to go with your scout's opinon regardless of whether "Clutch" exists.
If you're a computer game designer, though, you look at the problem differently. If you consider putting "clutch" into the game and you don't have any data whatsoever to use to design your algorithm, you risk screwing things up if you just pull the algorithm out of your tail end.
