Point-in-time (PIT) data reflects what was actually known at a specific historical moment. This is critically important for backtesting and research because using restated or revised data introduces look-ahead bias — incorporating information that wasn't available when decisions would have been made.
For example, a company might report Q1 earnings in April, then restate them in July. If your data uses the restated figures for April, your backtest would be using future information, making results artificially optimistic. PIT data uses the original figures as they were published.
Survivorship bias occurs when analysis only includes companies that still exist today, ignoring those that went bankrupt, were acquired, or delisted. This makes historical performance appear better than it actually was because failed companies are excluded.
A study of stock returns since 2000 that only includes currently active companies would exclude all the companies that failed during the 2008 financial crisis, dramatically overstating returns. Rigorous analysis must account for survivorship bias by including delisted securities.
← Back to all investing concepts