Survivorship Bias in Stock Backtests and Delisted Securities
Summary
The document explains how survivorship bias can affect stock strategy backtests. A universe built from stocks that exist today may omit companies that have since delisted, leaving historical tests with a stronger-looking set of securities than investors could actually have selected at the time. This can make simulated performance look better than live or historically feasible results.
It says BigQuant includes delisted stocks in its stock universe to address this source of bias. The document offers no independent test, details about how historical membership is reconstructed, or discussion of other backtest biases such as look-ahead bias, overfitting, and execution assumptions. Including delisted securities is a relevant safeguard, but by itself does not establish that a backtest is free from survivorship bias or that simulated results will match trading outcomes.
Key ideas
- A stock universe containing only currently listed companies can exclude past failures and delisted securities.
- That omission can inflate historical strategy performance relative to what was achievable.
- The platform says its universe includes delisted stocks to reduce survivorship bias.
- The document provides no independent validation or details on the platform's historical universe construction.
Tags
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.