Tell a real edge from luck.

A range around a measured statistic that quantifies how uncertain the measurement is. A 95% confidence interval (CI) says: "we are 95% confident the true value lies within this range."

A true, repeatable statistical advantage in a strategy's rules over the market. Edge is the underlying truth that metrics like win rate, profit factor, and Sharpe estimate — never observe directly.

The count of profitable trades a strategy produced. For low-win-rate strategies (most trend-followers), this is often the binding statistical constraint — more binding than total trade count.

The number of independent observations (trades) used to compute a metric. Bigger sample = sharper estimate.

A property of a strategy's rules: how often the entry conditions fire. A selective (picky) strategy generates few entries; a permissive one generates many. Selectivity is unrelated to per-trade confidence.

The minimum number of trades needed for a measured Sharpe ratio to be statistically distinguishable from zero. Tells you how many trades it takes to prove "this strategy is better than random."

Two observations are statistically independent when knowing one tells you nothing about the other. Sample-size benefits — tighter confidence intervals, stronger significance — only apply to independent observations. Correlated observations look like more data but don't behave like it.

A measurement is statistically significant when the observed pattern is unlikely to have occurred by random chance. In strategy evaluation, it means we have enough trades to trust that the observed metrics reflect a true underlying edge.

Combining results from multiple independent backtests (or studies) into one pooled estimate, by weighting each result by its precision (inverse-variance weighting). The proper way to summarize per-venue or per-period results — but ONLY when those results are genuinely independent.

When you pick the best-looking variants from a large pool, the winners' apparent performance is inflated — some of it is real edge, some of it is luck that happens to land on the strategies you picked. The more variants you test, the larger the inflation.

A strategy's return minus the buy-and-hold return over the same window — "how much it beat, or trailed, just holding the coin." Positive = the strategy added value; negative = holding won.

The benchmark return of simply buying the coin at the start of the window and holding it to the end, unleveraged (1×). The honest yardstick every strategy is measured against — "could you have beaten doing nothing?"

The decline in account equity from a peak to a subsequent trough. Reported in dollars (DD$) and as a percentage of the peak (DD%). The single most important risk metric for any leveraged strategy.

A return profile where most trades are small losers but a few rare winners are huge — the few big wins carry the entire profit.

Gross profit divided by gross loss — the total won across all winning trades, divided by the total lost across all losing trades. Above 1 means the strategy made money; below 1 means it lost.

Return measured relative to the risk taken to earn it, not in isolation. The honest way to compare a strategy against buy-and-hold — because two strategies with the same return can have wildly different drawdowns, and the one that suffered less pain is the better one.

Mean per-trade return divided by the volatility (the standard deviation, or spread) of those returns. It measures edge per unit of noise — how much return you earned for the bumpiness you endured. Higher is better; here it is computed per trade, not annualized.

A false signal: you enter on what looks like a breakout, price immediately reverses, and you exit at a small loss. Repeated whipsaws are how trend-following strategies bleed in choppy markets.

The share of closed trades that ended in profit, as a percentage. 40 wins out of 100 trades = a 40% win rate. On its own it says nothing about how much each win or loss was worth.

A (strategy, symbol) pair stops trading when its equity reaches or falls below a configured floor. This is the simulator's account-survival model: the moment that closes the gap between "the strategy stopped making money" and "the account that would have funded the strategy no longer exists."

A position-size multiplier. At 10× leverage a $1,000 account controls a $10,000 position. Leverage scales your profit, your loss, and your liquidation risk by the same factor — but it never changes which trades a strategy takes.

The probability that an account's equity drops below a critical threshold (zero, a margin floor, or a personal capitulation level) before the strategy realizes its expected return. The dominant risk metric for leveraged trading — much more important than expected return for assessing real-world deployment.

A trend-following entry signal that fires when a fast Exponential Moving Average crosses a slow one.

An EMA period is counted in candles, so its real-world lookback = period × candle duration — which means each fast/slow EMA pair only makes sense on a matching band of timeframes.

An informal measure of how much a market's short-term price wiggle (noise) overwhelms its longer-term direction (trend). Trend-following systems work when this ratio is low; they fail when it is high.

strategy family

A class of strategy that assumes "price in motion tends to stay in motion" — entries are placed in the direction of an established recent move.

The prevailing character of a market over a given period: trending up, trending down, choppy (sideways), or volatile.

The periodic payment exchanged between longs and shorts on a perpetual futures contract that tethers the perp price to the underlying spot price. In a bull market it is usually positive — longs pay shorts. The single biggest perp-specific cost the simulator does NOT model.

The set of dimensions on which the backtest accounting in this repo matches — and does not match — what a real account on a real perp venue would experience for the same trade signals.