Quant Memo
Statistics/●●●●●

How much does your prior matter? Watch it wash out

Asked at Jump Trading

Two analysts estimate a coin's bias. One uses a weak prior, Beta(1,1)(1,1) (uniform, "no idea"); the other a strong prior, Beta(50,50)(50,50) ("almost surely near fair"). They then see the same data.

Explain how prior strength governs how fast beliefs update, whether the two analysts converge, and the one prior that would prevent convergence forever.

Your answer

This one is open-ended. Work it through, then check your reasoning against the full solution.

More Statistics questions