The paper presents evidence that econometric techniques based on variance-L2 norm-are flawed and do not replicate. The result is un-computability of the role of tail events. The paper proposes a methodology to calibrate decisions to the degree (and computability) of forecast error. It classifies decision payoffs in two types: simple (true/false or binary) and complex (higher moments); and randomness into type-1 (thin tails) and type-2 (true fat tails), and shows the errors for the estimation of small probability payoffs for type 2 randomness. The fourth quadrant is where payoffs are complex with type-2 randomness. We propose solutions to mitigate the effect of the fourth quadrant, based on the nature of complex systems.
