Robustness

Test whether strategy behavior is sensitive to parameters or unstable out of sample.

Robustness checks help reduce overclaiming. A strategy that works only for one parameter set or only in-sample may not be reliable.

MA Parameter Sensitivity

Robustness read: similar results across parameter pairs are more credible than one isolated winner.

This is not optimization. It checks whether the strategy is robust across reasonable parameter choices.

Default parameter pairs: 10 / 30, 20 / 60, 50 / 120, 50 / 200

Out-of-Sample Validation

Split the backtest into in-sample and out-of-sample periods to check whether the strategy generalizes beyond the initial research window.