1.x — Chapter 1 summary and quiz
1.x — Chapter 1 summary and quiz#
Chapter summary#
This chapter covered the return and volatility concepts needed to compute backtest performance metrics.
Key concepts#
- Simple return: ; in pandas,
pct_change(). - Volatility: standard deviation of returns; annualize with for daily data.
- Annualized return: scale mean daily return or total return to a yearly equivalent.
- Sharpe ratio: (annualized return − risk-free rate) / annualized volatility; risk-adjusted performance.
What we learned#
- 1.1 Returns and volatility: How to compute simple returns, total return, volatility, annualization, and a simple Sharpe ratio for use in Project 1 — Backtesting Engine.
Application#
Use these definitions in your backtester to report total return, annualized return, annualized volatility, and Sharpe ratio. Combine with Python & Pandas for data and Quant Research for interpreting results and risk.
Quiz time#
Question 1
What is the difference between simple return and log return? When might you use each?
Show Solution
Simple return is ; log return is . For small returns they are close. Simple returns are intuitive and easy to compound over a few periods; log returns add over time (sum of log returns = log of total gross return) and are often used in models and for long-horizon aggregation.
Question 2
If daily returns have mean 0.0005 and standard deviation 0.01, what are (approximately) the annualized return and annualized volatility (252 trading days)?
Show Solution
Annualized return (approximate): (about 13.4%). Annualized volatility: (about 15.9%).
Question 3
Why do we annualize returns and volatility when reporting backtest performance?
Show Solution
So we can compare strategies run over different lengths (e.g. 6 months vs. 2 years) and compare to benchmarks or risk-free rates quoted in annual terms. Annualization puts everything on a common scale (per year).