Statistics

Backtest

A simulation of how a strategy would have performed on historical data.

What makes one worthless: survivorship and look-ahead bias, absent transaction costs and market impact, and undisclosed multiple testing.

A high-turnover strategy that looks excellent gross frequently turns negative once realistic costs are applied, which is the first thing an experienced researcher checks.

The question to expect: "your backtest shows a Sharpe of 3 - what do you check first?" A strong answer runs the list above and asks how many variants were tried before this one, which is the question most candidates never think to ask themselves.

Full guide

Survivorship Bias and Other Data Traps

The biases that make backtests look better than reality - and the questions interviewers use to find out whether you know them.

Related terms

Practise this

Put it into practice

Knowing the definition is not the same as spotting where it applies under time pressure. Work the question bank free.

Start practising free

Browse the full quant interview glossary