Kaiser Fung writes on uncertainty and thinking probabilistically about events that have already transpired. The full post is worth a read, but this line sticks out for me:
The fact that you won the lottery does not change the fact that economically, it was silly to play the lottery in the first place.
This fallacy pops up all the time, in particular with investment returns. Making a lot of money does not automatically validate the strategy used to obtain it. Selling S&P 500 puts looks like a great strategy by every metric, so long as you aren't told the actual strategy -- it has relatively high, constant returns. But one day it fails spectacularly. Until that day, the put-seller is a hero. After that day, he's LTCM.
A solid investment strategy is marked by confidence in its process as much as in its outcome.
And, just because this seems an appropriate place to put it, my other favorite statistical fallacy:
The plural of "anecdote" is not "data".