Backtesting Concepts

Why traders simulate strategies on historical data, what backtesting proves, and what it doesn't.

The candle-by-candle execution loop, how positions open and close, and how the equity curve is built.

Lookahead bias, survivorship bias, overfitting, regime change, and other pitfalls that silently inflate backtest results.

How candle interval affects signal frequency and statistical significance, candle counts, and market coverage.

What crossovers, thresholds, and comparisons mean, AND vs OR logic, and multi-condition strategies.

What happens when a trade closes while the entry rule still holds, and when to wait for a fresh entry signal instead.

Reference a higher timeframe inside a single condition -- confirm a trade against the bigger-trend picture without leaking future data.

How long and short positions work, why they behave differently, and what to consider when backtesting each direction.

How protective exits work -- stop-loss, take-profit, trailing, break-even, and time-based exits -- how they interact with spreads and leverage, and the tradeoffs of tight vs wide levels.

How leverage multiplies both returns and drawdowns, and why 2x leverage is not twice as good.

How transaction costs eat into returns and why a profitable strategy on paper can lose money in practice.

Why raw return is meaningless without context -- buy-and-hold comparison, alpha/beta intuition, and relative performance.

Why 5 winning trades does not make a strategy -- sample size, confidence, and the danger of thin data.

Why strategies that look perfect on historical data fail live -- parameter count, degrees of freedom, and the danger of too many knobs.

Splitting data into training and validation periods -- why testing on the same data you designed on is circular.