by Lawrence E. Kochard, Luis Garcia-Feijóo, Peng Wang, Rodney N. Sullivan
Continue on SelfMadeQuant
Suggested foundations for trading research and honest backtests and volatility models and surfaces. Specialist prerequisites vary by paper.
Use only information available at the simulated decision time.
Separate model selection from the final evaluation.
Follow diffusion-based models and their assumptions.
Separate conditional volatility from observed returns.
Reconcile signals, executions, positions and P&L.
Include the costs that can erase a paper strategy.
Study a correlated stochastic-variance model.
Choose a reproducible strategy, specify the trading rule, and test what remains after costs and estimation uncertainty.
Start in discrete time, move to Brownian motion, then read the original pricing argument and simulate it.