Survivorship Bias

Survivorship bias creeps in when an analysis includes only the entities that made it to the present and silently drops the ones that failed. In markets, a universe built from today's index members excludes every company that went bankrupt, was acquired, or delisted along the way - and those are precisely the losers whose absence makes the past look far more profitable than it was.

The fix is to include the dead: a survivorship-free dataset carries delisted tickers and defunct entities with the dates they left, so a backtest sees the world as it was, not as it turned out. It is a close cousin of look-ahead bias, and together they are the two mistakes most likely to make a strategy look brilliant in research and lose money in production.