Re:Why we should care about the Nate Silver vs. Nassim Taleb...
by briantakita on Tuesday December 18, 2018 @10:11AM
(#18706914)
The author was expressing apparently advanced philosophy that is missing from normal discourse, so I can understand why it goes over most peoples' heads.
"Instead, epistemically uncertain events are ignored a priori and then FiveThirtyEight assumes wild fluctuations in a prediction from unforeseen events are a normal part of forecasting. Which should lead us to ask ‘If the model is ignoring some of the most consequential uncertainties, are we really getting a reliable probability?’"
We don't know what we don't know. Any probabilistic model is constructed with a snapshot of the perceived variables. If the model-maker is not able to conceive of variables, then they will not be in the model, which could have asymmetric effects on accuracy of the model.
"Instead, epistemically uncertain events are ignored a priori and then FiveThirtyEight assumes wild fluctuations in a prediction from unforeseen events are a normal part of forecasting. Which should lead us to ask ‘If the model is ignoring some of the most consequential uncertainties, are we really getting a reliable probability?’"
We don't know what we don't know. Any probabilistic model is constructed with a snapshot of the perceived variables. If the model-maker is not able to conceive of variables, then they will not be in the model, which could have asymmetric effects on accuracy of the model.