{"uid":"cap__pUN35HB71uMQR5QbVJ3Q","slug":"money-mind-multiple-testing-correction-abc62711","name":"Money Mind Multiple Testing Correction","description":"Pay-per-call adjudication for trading research.\nEleven gates that killed 35 of our own concepts. Is your backtest real, is your\nprice data real, is your t-stat inflated? USDC on Base, no account needed.","url":"https://money-mind-extract.onrender.com/multipletest?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method","body"],"properties":{"body":{"type":"object","description":"Use when you searched many strategies or parameter sets and kept the best one. Quoting that winner's solo p-value is the most common way a backtest lies. Give the number of things you tested and the winner's t-statistic; returns the family-wise p-value, the t you actually needed, and the t that pure"},"type":{"type":"string","const":"http"},"method":{"enum":["POST"],"type":"string"},"bodyType":{"enum":["json"],"type":"string"}},"additionalProperties":false},"output":{"type":"object","properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":{"type":"json","example":{"verdict":"DOES NOT SURVIVE","required_t_for_5pct_family_wise":4.05,"expected_best_t_from_noise_alone":3.116}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.2","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.2/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.2","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.2","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_eyzRbDcUbms6YHVLZiQMe","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.2","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Applies family-wise multiple testing correction to a backtest winner's t-statistic to determine if it survives statistical scrutiny after searching many strategies.","exampleAgentPrompt":"I tested 50 different parameter combinations for my momentum strategy and the best one had a t-statistic of 2.8 — can you run the multiple testing correction to tell me if that result actually survives at the 5% family-wise level?","exampleUseCases":[{"title":"Quant researcher validating backtest winner","prompt":"I ran 80 different strategy variants and kept the one with a t-stat of 3.4 — can you correct for the fact that I searched 80 of them and tell me whether the t-stat is still significant or just noise?"},{"title":"Algo trader checking parameter sweep","prompt":"I grid-searched 200 parameter combinations on my mean-reversion strategy and the winner has a t-statistic of 3.9. Does that actually survive multiple testing correction, or is it just the luckiest draw from 200 tries?"},{"title":"DeFi strategy developer screening results","prompt":"My team screened 30 different DeFi yield strategies and picked the one with t-stat 2.6. Before we allocate capital, tell me if that t-stat is real or inflated by the selection process."}],"resultDescription":"Returns a JSON object with a plain-English verdict (e.g. 'DOES NOT SURVIVE'), the minimum t-statistic required for significance at the 5% family-wise level given the number of tests run, and the expected best t-statistic you'd see from pure noise across that many trials.","failureModes":["Missing required fields (type, method, body) returns validation error","Number of strategies tested set to 1 makes correction trivial and may return unexpected results","Extremely large numbers of strategies tested may produce very high required-t thresholds that seem implausible","Payment not provided or insufficient USDC triggers 402 payment required","Malformed body schema returns HTTP 400"],"whenToPreferThis":"Use this endpoint when you have already identified a best-performing strategy or parameter set from a search across multiple candidates and need to know whether its t-statistic is genuinely significant or inflated by selection bias. Prefer this over generic p-value calculators because it specifically accounts for family-wise error rate from multiple comparisons, returning the corrected threshold and expected noise baseline rather than just a raw p-value.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-18T12:45:35.426Z","isFirstParty":false,"canonicalSlug":"money-mind-multiple-testing-correction-abc62711"}