This book provides the trading system developer with a powerful set of statistical tools for measuring vital aspects of performance that are ignored by most developers.
All algorithms include intuitive justification, basic theory, all relevant equations, and highly commented C++ code for complete programs that run in a Windows Command Console.
Reprogramming them in other languages should be easy, given the detailed explanations of each algorithm.
The following topics are covered:
Testing for overfitting at the earliest possible stage
Evaluating the luckiness-versus-skill of a fully developed system before deploying it
Testing the effectiveness and reliability of a trading system factory
Removing selection bias when screening a large number of indicators
Probability bounds for future mean returns
Bounding typical and catastrophic future drawdowns
Is the best indicator or model in a competition truly the best, or just the luckiest?
Which markets provide truly superior profits for your trading system?
What holding time for your system provides the best risk/return performance?