Financial data glossary
Five terms decide whether a historical dataset can be trusted. None of them is difficult, and all of them are easy to get wrong by accident.
What is point-in-time data?
Point-in-time data is financial data exactly as it looked on a given date, rather than as it looks today. If a company later restated a figure, a point-in-time query for the original date still returns the original number — the restatement is walled off behind its own date.
Read more on point-in-time dataWhat is look-ahead bias?
Look-ahead bias is when a model uses information that was not yet public at the moment it claims to have acted. It makes a strategy look better than it could ever have performed, because the simulated decision was made with facts that only existed later.
Read more on look-ahead biasWhat is survivorship bias in financial data?
Survivorship bias is what happens when a dataset contains only the companies that still exist. Firms that were delisted, acquired, or went bankrupt are missing, so any historical study run on that universe silently excludes most of the ways an investment can go wrong.
Read more on survivorship biasWhat is a financial restatement?
A restatement is when a company reports a different value for a figure it has already published. Some are announced — in an amended filing, or an 8-K telling investors the original statements should no longer be relied upon — but most changes arrive quietly inside a routine later filing.
Read more on restatementWhat is fact lineage?
Fact lineage is the record connecting a number to the exact document it came from. A figure with lineage can be resolved back to its source filing, the period it covers, and the moment it became public — so a reader can check it rather than trust it.
Read more on fact lineage