LogFAQs > #934385977

Corrik7 posted...

I understand the point of it. It's to find the likeliest outcome and to identify other likely outcomes.

But, it seems negligent that any time the outcome isn't your likeliest outcome (or a significantly high outcome) to just handwave it away as well, that was always a possibility tho an unlikely one.

At the end of the day, Nate should be judged on whether his likeliest outcome (or likeliest if similar odds ones exist) come to fruition.

It shouldn't be well the outcome was just unlikely, as you can see. The outcome if such an outlier happens to your model should be that you were wrong in your model and finding out where you went wrong. Not just being like, well, only 1 time in a 100 would that happen.

No, if he claims 100 races are 70/30, he should be judged on whether the 70 candidates won roughly 70 of those races. If they won 95 or 50 of them, his model was likely wrong.

---

Congrats to Advokaiser for winning the CBX Guru Challenge!