CASE 09
Risk of Ruin Is Not Maximum Drawdown
An 18% historical maximum drawdown can coexist with a double-digit ruin probability if position size makes unfavorable sequences lethal.
Validation verdict for ruin boundary
Maximum drawdown asks, “How deep was the worst peak-to-trough fall in this observed sequence?” Risk of ruin asks, “Under stated simulation and sizing assumptions, how often is a defined capital boundary crossed?” They are not interchangeable.
What the headline metric obscures about ruin boundary
A modest historical maximum drawdown is often treated as a safety certificate. But the historical trade order is only one ordering, and the chosen sample may never have clustered the losses in the most damaging way.
Conversely, a deeper historical drawdown does not automatically imply higher ruin risk if position size is smaller, the threshold is distant and the payoff distribution has enough recovery capacity. Definitions matter more than labels.
How ruin boundary enters the backtest
One path versus a distribution of paths
Maximum drawdown is measured on the observed equity path; ruin is estimated across reshuffled or resampled paths under a specific model.
Ruin requires a threshold
A 20%, 50% or margin-based capital boundary produces different probabilities. “Ruin” is undefined without the boundary.
Sizing changes ruin nonlinearly
Increasing risk per trade magnifies both loss steps and the compounding damage from adverse sequences.
Simulation design changes the answer
Permutation, bootstrap, block resampling and assumptions about dependence can yield different tail frequencies.
Compact reconstruction of ruin boundary
| Strategy / sizing | Historical max DD | Ruin threshold | Simulated ruin frequency | Key driver |
|---|---|---|---|---|
| A at 2.0% risk/trade | −18% | −50% capital | 12% | Sequence + size |
| A at 0.5% risk/trade | −5% | −50% capital | 0.2% | Lower step size |
| B at 0.5% risk/trade | −27% | −50% capital | 1.0% | Bad observed path |
| B, threshold −30% | −27% | −30% capital | 9% | Closer boundary |
Strategy B has the deeper historical drawdown, yet A at aggressive sizing has the higher ruin frequency. Changing only the threshold also changes B’s ruin estimate. The number is conditional, not an intrinsic property of the strategy name.
The test that can overturn the ruin boundary verdict
Write the definition beside every ruin estimate: starting capital, risk per trade, threshold, resampling method, number of simulations, seed policy and whether trade dependence is preserved.
What trade-list analysis can and cannot identify about ruin boundary
Export-level red flags for ruin boundary
- Risk of ruin is shown without a threshold
- The same ruin number is reused across different position sizes
- Historical max DD is presented as the worst possible future loss
- Simulation method and dependence assumptions are omitted
- A low ruin probability is quoted from too few simulations or a narrow sample
What the export reveals about ruin boundary
- Observed maximum drawdown, recovery and underwater duration from the supplied path
- Conditional ruin frequency under user-defined capital thresholds and sizing assumptions
- Distribution of simulated maximum drawdowns, losing streaks and ending capital
- Sensitivity of ruin to size, threshold, resampling method and cost stress
What ruin boundary still requires from settings, code, or market data
- Simulation does not predict an exact future probability. It maps the consequences of the chosen model and observed data.
- Resampling cannot include losses absent from history, such as unprecedented gaps, fraud, venue failure or code malfunction unless explicit stress events are added.
Turn probability of hitting an absorbing boundary into a falsifiable backtest diagnosis.
Case file 09/20 · ABSORB · one failure mechanism, one falsifiable protocol
Research abstract: ruin boundary
Case file 09/20 · ABSORB · one failure mechanism, one falsifiable protocol
This article tests one central proposition: historical maximum drawdown is a statistic from one realized path, not the probability of hitting a boundary on future paths. The question is not merely whether the displayed net profit or win rate was arithmetically calculated. The deeper identification problem is whether we know what constitutes one observation, what information was available at the decision time, which assumptions are necessary for the profit to exist, and how much of the conclusion survives when those assumptions are perturbed. The research object is therefore not one performance table; it is the linked data-generation, fill-generation, estimation, selection, and capital-allocation process.
The primary estimand is the probability that a future path hits an absorbing capital, margin, or shutdown boundary. The observation unit is defined as capital paths generated by preserving or block-resampling trade order. Without this definition, split fills, duplicated signals, common events, synthetic prices, or timestamp conversions can be double-counted as independent evidence. A larger row count does not necessarily contain more independent information. An academically defensible analysis fixes the relationship between the observation unit and the estimand before it reports sample size, standard error, or statistical confidence.
The principal sensitivity axes are ruin boundary, block length, loss multiplier, and leverage. The hidden state is unseen sequencing, loss clusters, position-sizing feedback, and shutdown rules. In particular, an unobserved loss ordering can trigger margin failure earlier even with the same set of trades. Means and medians alone are incapable of describing that mechanism, so the analysis combines central estimates with lower quantiles, expected shortfall, sign stability, boundary-hitting frequency, and contribution concentration. The objective is not to find one pessimistic number, but to map the full region in which the original conclusion changes sign or ceases to be economically usable.
The conclusion does not attempt to prove that a backtest is good. It separates the component that remains after attempted falsification from the component that disappears when assumptions are reconstructed. The governing decision principle is to retain maximum drawdown as a descriptive statistic while separately estimating hitting probabilities and time-to-hit across several boundaries. This is not trading advice; it is a research procedure for measuring how much evidentiary weight a TradingView trade export can carry. Liquidity not present in the file, broker-specific rules, future regimes, outages, and gaps require separate evidence, and statistical survival never guarantees future profit.
The numerical values illustrate the method for probability of hitting an absorbing boundary; they are not a real strategy, client record, or forecast.
Hypotheses and identification target for ruin boundary
the probability that a future path hits an absorbing capital, margin, or shutdown boundary
H₀ for ruin boundary: The reported performance is not materially dependent on the suspected failure mechanism and survives reasonable perturbations.
H₁ for ruin boundary: The reported performance depends materially on the suspected failure mechanism and deteriorates after reconstruction, perturbation, or dependence-aware resampling.
the probability that a future path hits an absorbing capital, margin, or shutdown boundary
capital paths generated by preserving or block-resampling trade order
unseen sequencing, loss clusters, position-sizing feedback, and shutdown rules
ruin boundary, block length, loss multiplier, and leverage
Formal estimands for ruin boundary
Definitions precede inference.
τ_B = inf{t : W_t ≤ B}First time wealth reaches the pre-specified absorbing boundary B.ψ_H(w)=P_w(τ_B≤H)Finite-horizon probability of reaching the boundary from initial wealth w.H_t=max_{s≤t}W_s, MDD=max_t(1−W_t/H_t)Maximum drawdown observed on one realized path.The primary estimand is the probability that a future path hits an absorbing capital, margin, or shutdown boundary. The observation unit is defined as capital paths generated by preserving or block-resampling trade order. Without this definition, split fills, duplicated signals, common events, synthetic prices, or timestamp conversions can be double-counted as independent evidence. A larger row count does not necessarily contain more independent information. An academically defensible analysis fixes the relationship between the observation unit and the estimand before it reports sample size, standard error, or statistical confidence.
The principal sensitivity axes are ruin boundary, block length, loss multiplier, and leverage. The hidden state is unseen sequencing, loss clusters, position-sizing feedback, and shutdown rules. In particular, an unobserved loss ordering can trigger margin failure earlier even with the same set of trades. Means and medians alone are incapable of describing that mechanism, so the analysis combines central estimates with lower quantiles, expected shortfall, sign stability, boundary-hitting frequency, and contribution concentration. The objective is not to find one pessimistic number, but to map the full region in which the original conclusion changes sign or ceases to be economically usable.
Illustrative recomputation design for ruin boundary
For the ruin-boundary risk reconstruction, table values are illustrative calculations used to expose a verdict reversal; they are not a user’s observed TradingView result.
| ID | Recomputation layer | Operation | Comparison | Diagnostic purpose |
|---|---|---|---|---|
| S0 | Reported result | Restate the Strategy Tester aggregate | Base | Apparent conclusion |
| S1 | Unit reconstruction | capital paths generated by preserving or block-resampling trade order | Reassess count and dependence | Information correction |
| S2 | Independent recomputation | Rebuild price, size, cost, and currency row by row | Separate reconciliation error | Measurement validity |
| S3 | Local stress | ruin boundary, block length, loss multiplier, and leverage | Perturb one factor only | Causal sensitivity |
| S4 | Tail injection | an unobserved loss ordering can trigger margin failure earlier even with the same set of trades | Recompute lower quantiles and boundary hits | Capital preservation |
| S5 | Dependence-aware resampling | Generate paths across several block lengths | Intervals and sign stability | Estimation uncertainty |
| S6 | Selection adjustment | Log search, OOS review, and exclusions | Correct maximum-selection bias | Generalization |
| S7 | Full gate | retain maximum drawdown as a descriptive statistic while separately estimating hitting probabilities and time-to-hit across several boundaries | Compare with predeclared thresholds | Pass / hold / reject |
The illustrative recomputation for ruin boundary changes one processing layer at a time, then combines only predeclared layers. S0 is never treated as ground truth; it is the statement to be audited. S1 and S2 ask whether the exported unit and arithmetic are coherent. S3 and S4 identify local sensitivity and tail failure. S5 changes the uncertainty model rather than the trade list. S6 adjusts for the search that preceded publication. S7 applies the same gate to every version. This order prevents an adverse result from being explained away by simultaneously changing several assumptions.
In the ruin-boundary risk figures, color and position encode diagnostic sensitivity only; they do not represent statistical significance or future P&L.
Diagnostic figures specific to ruin boundary
Four separate visual tests; no decorative chart reuse.
Multi-layer audit questions for ruin boundary
A result is only as strong as its weakest unresolved layer.
For third-party reproduction, fix the estimand as “the probability that a future path hits an absorbing capital, margin, or shutdown boundary.” Do not substitute net profit, win rate, or a visually smooth curve for that target. Declare the horizon, account currency, included frictions, and operating-stop boundary before calculation. Any post-result change creates a new hypothesis and version, preventing the question from being selected after the answer is known.
Reconstruct the observation unit as “capital paths generated by preserving or block-resampling trade order” before treating rows as independent evidence. Report raw rows, parent trades, decisions, event clusters, and the denominator used for each average or standard error. Recompute finite-horizon ruin probability, first-passage-time distribution, maximum drawdown, margin-boundary rate, and mandate-stop rate under more than one defensible aggregation rule so that a larger export is not mistaken for a larger information set.
Preserve the hash of the TradingView export and the symbol, timeframe, session, timezone, order-processing settings, costs, account currency, and Pine version. For probability of hitting an absorbing boundary, unseen sequencing, loss clusters, position-sizing feedback, and shutdown rules directly affects reproducibility. Keep immutable source, normalized, and analysis layers separate, with every join, deletion, imputation, and conversion recorded in a transformation ledger.
The export identifies only what can be rebuilt from recorded time, price, quantity, and P&L. broker liquidation order, margin-call mechanics, negative-balance protection, and order suspension requires additional evidence. Mark each causal link as observed, bounded by assumption, or externally unverified. This prevents unseen sequencing, loss clusters, position-sizing feedback, and shutdown rules from being presented as a confirmed fact when the available data support only an interval or conditional conclusion.
Do not adopt the platform summary as ground truth. Independently state the wealth recursion including sequence, sizing, margin, and stop rules, then calculate first-passage times to several absorbing boundaries on every path. Reconcile total and row-level differences by sign, date, symbol, and order type. If discrepancies concentrate in the exact state associated with probability of hitting an absorbing boundary, treat that concentration as a primary finding rather than dismissing it as rounding.
Report finite-horizon ruin probability, first-passage-time distribution, maximum drawdown, margin-boundary rate, and mandate-stop rate with intervals or resampling distributions, not point estimates alone. Match the uncertainty method to sample size, skewness, heavy tails, censoring, and selection history. If normal, quantile, and dependence-aware methods disagree on the sign, classify the edge as unidentified and show the minimum detectable effect and lower decision bound.
Do not narrow uncertainty with an IID shuffle alone. Resample trade blocks that preserve loss clustering and regime persistence using several fixed block lengths and stationary bootstrap. Preserve random seed, repetition count, wrap rule, and missing-data treatment. For each block specification, report the distribution of finite-horizon ruin probability, first-passage-time distribution, maximum drawdown, margin-boundary rate, and mandate-stop rate, the rejection-side tail mass, and the rate at which the verdict changes sign.
Interrogate the mechanism “unseen sequencing, loss clusters, position-sizing feedback, and shutdown rules” with lower quantiles, expected shortfall, influence, cluster length, and boundary-hitting measures. Historical maximum loss is not a loss cap. Define several absorbing or operating boundaries—capital, margin, mandate drawdown, and recovery time—and record which boundary fails first under each stress.
A flat commission deduction is not an execution model for probability of hitting an absorbing boundary. Allocate spread, slippage, financing, borrow, roll, conversion, rounding, and rejected orders to the relevant unit. Recompute finite-horizon ruin probability, first-passage-time distribution, maximum drawdown, margin-boundary rate, and mandate-stop rate under base, upper-quantile, and crisis states while preserving the possibility that costs and losses worsen together.
Count the complete population of periods, symbols, timeframes, parameters, exits, filters, and metrics that were tried. Do not detach the attractive result for probability of hitting an absorbing boundary from rejected candidates, interim changes, or repeated validation reviews. Where appropriate, use PBO, SPA, and a Deflated Sharpe Ratio, and treat an unrecorded trial count as a material audit limitation.
Test whether probability of hitting an absorbing boundary is concentrated in one trend, volatility, liquidity, rate, or session state. Define regimes prospectively or on training data only. Report statewise finite-horizon ruin probability, first-passage-time distribution, maximum drawdown, margin-boundary rate, and mandate-stop rate, occupancy, transition probabilities, and costs, then reweight the mixture to adverse but realistic future compositions.
For the ruin boundary case, the same trade set can follow different capital paths under another inception date, order, initial balance, rounding rule, or stop condition. Separate fixed quantity, fixed R, and percentage sizing, then use circular shifts and block orderings to recompute drawdown, recovery, and boundary hits. Equal terminal P&L does not imply equal path risk.
Perturb “ruin boundary, block length, loss multiplier, and leverage” one axis at a time before creating a joint sensitivity surface. Add the negative control “compare sequences with the same historical maximum drawdown but different loss ordering to demonstrate that the maximum alone does not determine ruin risk.” Predefine the grid and crisis rule so that neither the most favorable nor the most damaging cell is selected after inspection. Save the slope, curvature, and exact point where the decision boundary is crossed.
Have a second implementation state the wealth recursion including sequence, sizing, margin, and stop rules, then calculate first-passage times to several absorbing boundaries on every path, then compare critical row-level outputs. Regression fixtures should include empty files, duplicate timestamps, extreme costs, reverse ordering, missing values, and boundary cases. Agreement between implementations is insufficient if they share the same bad input, so separate data construction and review roles where feasible.
Predeclare the decision rule. This case passes only if “ruin, margin, and mandate-stop probabilities remain below predeclared limits across defensible block lengths and loss stresses.” Near a boundary, disclose interval width and economic materiality rather than a binary badge. If only one favorable block length, cost state, or implementation passes, classify the result as assumption-sensitive rather than robust.
The evidence ledger must store the input hash, code version, settings, exclusions, “ruin boundary, block length, loss multiplier, and leverage,” block lengths, random seed, repetition count, and every scenario output. Keep exploratory and confirmatory results in separate namespaces and retain failed trials. When new TradingView data arrive, create a new version and track distance to boundary, losing-cluster length, leverage, margin headroom, and boundary-hitting probability rather than overwriting the old result.
Translate statistical changes into capital consequences. A shift in expectancy, lower quantile, recovery time, or boundary risk caused by probability of hitting an absorbing boundary should be mapped to trade count, capital, margin, and continuation. A small per-trade difference can compound under high turnover, while a rare loss can be decisive near an absorbing boundary.
Separate hypothesis design, implementation, independent recalculation, and approval where practical. Stop automatically on material reconciliation error, unresolved missing data, non-reproducibility, or a predeclared threshold breach. Audit the chain “one historical path → observe only maximum drawdown → ignore alternative orderings → understate boundary-hitting risk → capital loss,” and monitor distance to boundary, losing-cluster length, leverage, margin headroom, and boundary-hitting probability prospectively without turning a historical pass into a promise of future profit.
Falsification protocol for ruin boundary
retain maximum drawdown as a descriptive statistic while separately estimating hitting probabilities and time-to-hit across several boundaries
Freeze the TradingView source for the ruin boundary audit
Store the export without alteration and record its hash, export time, strategy, symbol, timeframe, and settings. Preserve every column relevant to probability of hitting an absorbing boundary; deletions and imputations belong only in derived tables.
Reconstruct the observation unit for ruin boundary
Aggregate rows into “capital paths generated by preserving or block-resampling trade order,” and report raw rows, parent trades, events, and independent clusters. Recompute the critical result under another defensible aggregation.
Independently recompute the displayed ruin boundary result
Independently state the wealth recursion including sequence, sizing, margin, and stop rules, then calculate first-passage times to several absorbing boundaries on every path. Reconcile row-level and aggregate outputs with Strategy Tester and preserve where discrepancies concentrate.
Isolate the ruin boundary mechanism
Treat probability of hitting an absorbing boundary as the principal mechanism and move “ruin boundary, block length, loss multiplier, and leverage” one axis at a time while holding other settings fixed.
Map the operating boundary for ruin boundary
Combine the primary and interacting axes on a predeclared grid and recompute finite-horizon ruin probability, first-passage-time distribution, maximum drawdown, margin-boundary rate, and mandate-stop rate. Record the width and connectivity of the acceptable region and every boundary crossing.
Resample the dependence structure relevant to ruin boundary
Use trade blocks that preserve loss clustering and regime persistence with several fixed block lengths and stationary bootstrap. Save every random seed, repetition count, and block specification.
Inspect influence points and operating boundaries for ruin boundary
For the ruin-boundary risk influence test, remove the largest contributor, top-k contributors, selected periods, and relevant regimes in sequence; then recompute lower-tail measures and the operating boundary.
Apply negative controls and conservative bounds to ruin boundary
Compare sequences with the same historical maximum drawdown but different loss ordering to demonstrate that the maximum alone does not determine ruin risk. Bound broker liquidation order, margin-call mechanics, negative-balance protection, and order suspension as unobserved factors rather than elevating the optimistic value into the final answer.
Apply the predeclared gate to ruin boundary
Do not move the threshold after seeing results. Compare with “ruin, margin, and mandate-stop probabilities remain below predeclared limits across defensible block lengths and loss stresses,” and distinguish pass, hold, and reject. Any unresolved material mismatch causes a hold.
Save a reproducible evidence package for ruin boundary
Bundle the source, transformation ledger, formulas, figures, all scenarios, failure logs, and code version for rerun in another environment. Prospectively monitor distance to boundary, losing-cluster length, leverage, margin headroom, and boundary-hitting probability.
Decision gate for ruin boundary
Reject the story before trusting the curve.
How to read the ruin boundary figures and equations
The figures for ruin boundary use illustrative recomputations constructed to expose this specific failure mode. Do not infer statistical significance from line position or color alone; first verify the estimand, units, denominator, censoring rule, and cost sign defined by the equations. A sensitivity surface is not a causal estimate. It shows how a conclusion changes only within the stated assumptions. Resampling should compare an IID shuffle with stationary and block bootstrap procedures across several block lengths so that loss clustering and regime persistence are not silently destroyed. Store the random seed, iteration count, block length, bandwidth, and missing-data treatment, and claim reproducibility only after an independent implementation reproduces the same aggregates.
This case passes only if “ruin, margin, and mandate-stop probabilities remain below predeclared limits across defensible block lengths and loss stresses” across reconstructed values, local perturbations, joint sensitivity, dependence-preserving resampling, and the negative control, with no material sign reversal or unresolved reconciliation error. A pass is limited evidence against the stated failure mode, not certification of future profit.
- The estimand and observation unit were fixed before outcomes were reviewed
- For ruin-boundary risk, any material disagreement between reported and independently recomputed values must be resolved or explicitly explained.
- The ruin-boundary risk claim passes this gate only when its acceptable stress region is broad and connected rather than one isolated favorable island.
- The sign of the ruin-boundary risk estimate must remain stable across defensible block lengths, saved seeds, and reasonable interval methods.
- For ruin boundary, economic margin remains after deleting the largest and top-five contributors and key regimes
- For ruin boundary, conservative cost, fill, and capital-boundary scenarios remain inside the stopping mandate
Limitations, external validity, and reproducibility of the ruin boundary audit
Every inference has a boundary.
The first limitation is that a trade export does not contain the complete market state. If order-book depth, queue position, network latency, rejected orders, broker liquidity, or realized financing history is absent, the probability that a future path hits an absorbing capital, margin, or shutdown boundary remains model-mediated. Model outputs should be displayed as scenario ranges and must not be formatted as though they were directly observed facts.
A second limitation specific to the ruin boundary analysis is structural change. A long historical sample does not guarantee a common population when market rules, participants, volatility, rates, spreads, data construction, or Pine execution semantics change. Do not increase nominal sample size by indiscriminately pooling old periods. Estimate rolling and regime-conditioned behavior and test parameter stability around detected changes.
A third limitation specific to the ruin boundary analysis is reuse of the diagnostic battery. Applying these tests repeatedly to the same data and editing the strategy until it passes turns the diagnostic process itself into another optimizer. Every post-test edit starts a new model version and requires untouched or prospective evidence. A test chosen after reading the outcome belongs to exploration and cannot be counted as independent confirmation.
A fourth limitation for the ruin boundary analysis is the distinction between statistical survival and operational suitability. Behavioral tolerance, locked capital, tax, regulation, outages, account terms, order-size limits, market-order restrictions, and liquidity discontinuities cannot be resolved from a CSV alone. The lab is a diagnostic for discovering hidden failure risk earlier; it is not investment advice, a performance warranty, or a guarantee of bounded loss. User-specific constraints remain a separate decision layer.
The estimand “the probability that a future path hits an absorbing capital, margin, or shutdown boundary” is identified only within the columns present in the TradingView export and the stated assumptions. If broker liquidation order, margin-call mechanics, negative-balance protection, and order suspension cannot be observed, report bounds rather than a false point estimate.
Past estimates of probability of hitting an absorbing boundary need not belong to the same population after changes in rules, participants, volatility, costs, or data specifications. Track distance to boundary, losing-cluster length, leverage, margin headroom, and boundary-hitting probability in rolling and regime-specific windows.
For ruin-boundary risk, repeatedly applying the same diagnostic battery and editing until it passes turns verification into another optimizer. Every post-audit change therefore creates a new model version and requires untouched evidence.
Even if ruin, margin, and mandate-stop probabilities remain below predeclared limits across defensible block lengths and loss stresses, the analysis does not establish tax, regulatory, behavioral, liquidity, order-size, or systems suitability. Separate statistical diagnosis from live-operating approval.
Deleting observations related to unseen sequencing, loss clusters, position-sizing feedback, and shutdown rules may improve the result. Compare no deletion, conservative imputation, and worst-case imputation, and display how finite-horizon ruin probability, first-passage-time distribution, maximum drawdown, margin-boundary rate, and mandate-stop rate changes.
Run the control “compare sequences with the same historical maximum drawdown but different loss ordering to demonstrate that the maximum alone does not determine ruin risk.” If the control performs similarly, suspect processing rules or common market drift before attributing performance to the strategy.
After a provisional pass, log distance to boundary, losing-cluster length, leverage, margin headroom, and boundary-hitting probability sequentially and stop on persistent departures from the predeclared predictive range. Diagnose implementation drift before reoptimizing history.
Multiple methods can agree because they share the same bad input or the same mechanism “unseen sequencing, loss clusters, position-sizing feedback, and shutdown rules.” Give lower-tail outcomes, failed scenarios, and unresolved mismatches the same visual prominence as favorable results; test count is not proof of correctness.
Independent and adversarial findings for ruin boundary
The ruin-boundary risk case has a separate review line for formulas, chart encodings, data definitions, and falsifiability so agreement on one layer cannot mask failure on another.
The formula audit checks numerator, denominator, sign, unit, domain, and every conditioning assumption as one system. The material caution for this case is: Maximum drawdown is a maximum on one realized path; risk of ruin is a probability across future paths. ψ_H(w) is undefined without the absorbing boundary B, horizon H, wealth recursion, and sizing rule. Do not convert historical MDD directly into a ruin probability. A correct symbolic expression can still calculate the wrong quantity when a column, currency, time unit, or fee sign is misdefined, so those mappings are part of the mathematical audit.
The figure audit assigns distinct jobs: Figure 1 diagnoses probability of hitting an absorbing boundary; Figure 2 maps joint sensitivity; Figure 3 shows the dependence-preserving distribution of finite-horizon boundary-hitting probability; Figure 4 traces causal propagation. Color denotes distance to a predeclared gate, not probability or observed performance. Axis units, zero, quantiles, censoring, and bounds must agree with captions and tables. A smooth SVG line is explanatory geometry, not evidence of estimation precision.
The adversarial test does not cherry-pick one hostile scenario. It uses the negative control “compare sequences with the same historical maximum drawdown but different loss ordering to demonstrate that the maximum alone does not determine ruin risk,” resamples trade blocks that preserve loss clustering and regime persistence at several block lengths, and bounds broker liquidation order, margin-call mechanics, negative-balance protection, and order suspension as unobserved factors. Repetitions, seeds, exclusions, block specifications, and plotting range are frozen before results so the implementer cannot tune the audit after seeing the answer.
The independent conclusion is restricted to whether “ruin, margin, and mandate-stop probabilities remain below predeclared limits across defensible block lengths and loss stresses.” It does not certify a good strategy or future profit. Any material reconciliation error, formula-domain violation, table-figure contradiction, sign reversal across defensible block lengths, or failure to outperform the negative control produces hold or reject. Prospectively, monitor distance to boundary, losing-cluster length, leverage, margin headroom, and boundary-hitting probability.
Methodological references for ruin boundary
Primary methods and official platform documentation.
- Politis, D. N. & Romano, J. P. (1994). The Stationary Bootstrap. JASA.
- Kaplan, E. L. & Meier, P. (1958). Nonparametric Estimation from Incomplete Observations. JASA.
- Newey, W. K. & West, K. D. (1987). A Simple, Positive Semi-definite, Heteroskedasticity and Autocorrelation Consistent Covariance Matrix. Econometrica.
- Efron, B. (1979). Bootstrap Methods: Another Look at the Jackknife. Annals of Statistics.
- Lo, A. W. (2002). The Statistics of Sharpe Ratios. Financial Analysts Journal.
- White, H. (2000). A Reality Check for Data Snooping. Econometrica.
- TradingView Pine Script® documentation: Strategies.
References for the ruin boundary case provide methodological context; they do not validate the synthetic numbers in this article or certify any backtest result. TradingView documentation is used for platform semantics, while statistical papers motivate uncertainty and selection controls.
Frequently asked questions about ruin boundary
Can maximum drawdown estimate ruin?
It informs sizing and tail context, but one historical depth is not a probability of crossing a future threshold.
What should “ruin” mean?
Define it operationally: for example, 50% capital loss, margin liquidation, minimum deployable capital or a strategy shutdown level.
Why does position size matter so much?
Larger risk per trade increases loss steps and leaves less capital for recovery, so adverse sequences can cross the boundary far more often.
Can a backtest exposed to ruin boundary be trusted?
Do not judge the ruin-boundary risk case from a finished equity curve alone. Use the TradingView trade list to inspect the mechanism-specific concentration, path, cost, timing, and dependence evidence shown on this page.
Important limitations for the ruin boundary analysis
This article provides educational, descriptive analysis of constructed backtest failure examples. It is not investment advice, a buy or sell signal, a forecast or a promise of performance. Backtest results depend on data, code, broker-emulator assumptions, costs, sizing and market structure. TradingView is a trademark of TradingView, Inc.; SG Group is independent and does not claim endorsement or sponsorship by TradingView.
Counterpart: 破産確率と最大ドローダウンは同じリスクではない