VIDYA (9/30, accelerates on volatility, as the formula says)
The trend's speed should respond to relative volatility: comparing the distribution of recent moves against a longer historical yardstick tells you whether the market is more agitated than its own normal. Volatility above normal slows the trend and volatility below it speeds it up, so the line is not turned by passing agitation and still keeps up with the market when it settles.
Measured in forex — EUR/USD and GBP/USD · daily bars built from 15m · 1 pip spread (~0.009% per round trip) · no survivorship bias
- ✓invariance
- ?costs
- ?placebo
- ✓benchmark
- ?out of sample
- ?multiple testing
At its worst the account was worth 0% less than its own best previous moment, and it spent 2,113 days below that peak.
What was measured
How many of those trades actually count
What it paid, before any deductions
Where it stalled · the broker's fee
What would have happened to the money
What this result does NOT say
- One market, one universe
- Measured on 2 spot currency pairs. It says nothing about futures, equities or indices, nor about how the same technique behaves in another market.
- One window of time, not every window
- The measured period runs from 2020-01-01 to 2026-06-26. A market moves through regimes, and a technique can work in one and fail in another — the card measures the regimes that fit inside this window, not the ones still to come.
- One cost structure
- The cost charged is a 1.0 pip spread, crossed once. Anyone paying more than that gets a worse result, and anyone paying less gets a better one — the verdict holds for this fee.
- One exit rule
- The trade was closed by: the technique itself (held until the opposite signal). The same entry measured with a different exit is a different strategy, and can earn a different verdict — it happens in this archive.
- The number of trades is not the sample size
- There are 616 trades, but only 233 independent market episodes: trades that overlap in time are not independent observations, and counting them as if they were inflates any result. It is the smaller number that governs the arithmetic. With 233 episodes, what the data supports is a range from -0.10% to +0.13% per trade — the published average is the centre of it, not the exact measurement.
- Daily bars
- Measured at the daily close. Nothing here measures what happens inside the day, and an intraday technique is not auditable with this data.
Numbers and reproducibility
The six controls
| control | status | t | threshold | episodes |
|---|---|---|---|---|
| invariance | passed | — | — | — |
| costs | inconclusive | 0.10 | 1.97 | 233 |
| placebo | inconclusive | 0.15 | 1.97 | 233 |
| benchmark | passed | — | — | — |
| out of sample | inconclusive | — | — | — |
| multiple testing | inconclusive | — | — | — |
- invariance616 signals across 4055 bars
- costsgross +0.014% · cost 0.008% · net +0.006% (t=0.10)
- placeboactual +0.006% · placebo -0.003% · excess +0.009% ± 0.058% (t=0.15 against a threshold of 1.97, 233 real groups, 30,800 sham dates, draw error ±0.007%) — the status flips inside the placebo's own Monte Carlo error
- benchmarktechnique +0.01% · buy and hold (same horizon) +0.01% · excess +0.00%
- out of sampleasset half A: +0.001% (t=0.01, 179 episodes) · asset half B: +0.011% (t=0.17, 180 episodes) · liquid half (>= US$ 0/day): +0.006% (t=0.10, 233 episodes) · period 1/4 (2020-02-05 a 2021-09-15): +0.118% (t=0.84, 62 episodes) · period 2/4 (2021-09-16 a 2023-05-11): -0.033% (t=-0.28, 63 episodes) · period 3/4 (2023-05-15 a 2025-02-02): +0.002% (t=0.02, 59 episodes) · period 4/4 (2025-02-03 a 2026-06-14): -0.064% (t=-0.67, 52 episodes)
- multiple testing1 variation(s) tested · t=0.10 across 233 episodes (equivalent to t=0.10) · p≈0.9221 · false positives expected by chance ≈ 0.92
Equity — outside the six controls, and here is why
The t of the trade series is invariant to bet size: 0.5%, 1% and 3% agree to the sixth decimal. Nothing here moves the verdict — it moves what the account would have lived through.
- risking 1.0% per trade
- ×1.00
- worst drawdown from the peak
- −0%
- days below the previous peak
- 2,113
- signals refused for lack of capital
- 0%
- paths where the account halved (out of 12)
- 0
Reproducibility
- period
- 2020-01-01 to 2026-06-26
- assets that traded
- 2
- variations tested before this one
- 1
- gross per trade
- +0.01%
- net per trade
- +0.01%
- exit rule
- the technique itself (held until the opposite signal)
- median duration bars
- 3
- mean duration bars
- 6.5
- max duration bars
- 56
- spread pips
- 1.0
- episode days
- 7
- seed
- 20260728
- short deviation
- 9
- long deviation
- 30
- smoothing period
- 9
- fixed constant
- 0.2
- reading
- formula
Twelve Data forex (15m aggregated to 1d) · collected on 2026-07-25 · 2 assets · 4,055 bars · 2020-01-01 to 2026-06-26
Hypothesis, filed before the result
Corrects this declaration BEFORE measuring. It said the prose contradicts the formula and that both readings would be measured; on a careful re-reading of the source, this is a DEFECT OF DESCRIPTION and not an ambiguity of specification — the same case as the KAMA's '25 to 900'. The chain in the text has three links and the first two are right: higher volatility ⇒ higher ratio ⇒ higher constant. Only the third errs, concluding 'a slower trend' when a higher constant is FASTER. Since the source describes the ratio and the constant correctly, the formula is the specified technique and there is ONE card, not two. The evidence that settles it: inverting k to obtain the behaviour the text states produces a recursion that DIVERGES with the source's own parameters — measured over 17,154 bars, k·s never exceeds 0.37 in the formula, and inverted it exceeds 1 on 6.62% of the bars (maximum 4.31, the series blowing up to infinity), because inverted k grows when recent volatility is LOW. Nobody specifies a technique that explodes when the market calms down. The prediction that stands: the VIDYA accelerates on volatility, so it turns over more than the KAMA and is the one that depends most on cost. A measured property to record on the card: the specified k uses the standard deviation of PRICES, which grows with the window even without volatility — on a zero-noise ramp k=0.3111, pure arithmetic of the window. In BTC the median k over prices is 0.538 against 0.927 over returns. The source suggests returns ('the result may possibly benefit'), but does not specify it; we audit the specified version. Family prediction, filed before measuring: (1) none of the adaptive averages survives the family's Benjamini-Hochberg in crypto; (2) the control that kills the most will be COST, not the benchmark — unlike the chart-pattern census, where the benchmark was the gravedigger, because these are always-in-the-market systems and they turn over a lot; (3) each adaptive average will have HIGHER turnover than its fixed-period counterpart already in the archive, and will die more at cost than it does. The mechanism is in the source itself: Table 17.1 reports a profit factor 'even before costs' and states that success is 'inversely related to the average number of trades' (KAMA 159 trades, factor 1.53; VIDYA 443, factor 1.17). That is a cost story told as a quality story. If I am wrong and one survives cost with higher turnover, the chapter's thesis gains evidence it did not present. MEASURED IN FOREX (EUR/USD and GBP/USD, daily bars built from 15m), not in crypto. This is a pre-registered REPLICATION of the same technique in the second market — not a new discovery — and the multiple-testing count treats it as such. What changes relative to the crypto card: 2 pairs over 6.5 years against 540 over 9, a round trip costs about 20× less (a 1 pip spread crossed once, against 0.1% commission per leg), the detection floor is about 10× lower (0.092% against 0.97%) and there is NO survivorship bias, because a currency pair does not get delisted. Specific prediction: with only 2 assets, the independent episodes come from TIME and not from the variety of assets, so I expect a low effective N and a high proportion of INCONCLUSIVE — and whatever is asserted here is worth more than in crypto, because cost cannot be the gravedigger.
filed on 2026-07-31, before the number existed
The original, as it was filed
Corrige esta declaração ANTES de medir. Ela dizia que a prosa contradiz a fórmula e que as duas leituras seriam medidas; relendo a fonte com cuidado, é DEFEITO DE DESCRIÇÃO e não ambiguidade de especificação — mesmo caso do '25 a 900' da KAMA. A cadeia do texto tem três elos e os dois primeiros estão certos: volatilidade maior ⇒ razão maior ⇒ constante maior. Só o terceiro erra, ao concluir 'tendência mais lenta' quando constante maior é mais RÁPIDA. Como a fonte descreve corretamente a razão e a constante, a fórmula é a técnica especificada e há UM card, não dois. Evidência que fecha a questão: inverter k para obter o comportamento que o texto enuncia produz recursão que DIVERGE com os parâmetros da própria fonte — medido em 17.154 velas, k·s nunca passa de 0,37 na fórmula, e invertido passa de 1 em 6,62% das velas (máximo 4,31, série estourando para infinito), porque invertido k cresce quando a volatilidade recente é BAIXA. Ninguém especifica uma técnica que explode quando o mercado se acalma. Previsão que fica de pé: a VIDYA acelera na volatilidade, então gira mais que a KAMA e é a que mais depende do custo. ⚠️ Propriedade medida a registrar no card: o k especificado usa o desvio dos PREÇOS, que cresce com a janela mesmo sem volatilidade — numa rampa de ruído zero k=0,3111, pura aritmética de janela. Em BTC a mediana de k sobre preços é 0,538 contra 0,927 sobre retornos. A fonte sugere retornos ('é possível que o resultado se beneficie'), mas não especifica; auditamos a versão especificada. Previsão da família, registrada antes de medir: (1) nenhuma das adaptativas sobrevive ao Benjamini-Hochberg da família em cripto; (2) o controle que mais mata será o CUSTO, e não o benchmark — diferente do censo de padrões gráficos, onde o benchmark foi o coveiro, porque estas são sistemas sempre-no-mercado e giram muito; (3) cada adaptativa terá giro MAIOR que a sua contraparte de período fixo já no corpus, e morrerá mais no custo do que ela. O mecanismo está na própria fonte: a Tabela 17.1 relata fator de lucro 'even before costs' e afirma que o sucesso é 'inversely related to the average number of trades' (KAMA 159 operações, fator 1,53; VIDYA 443, fator 1,17). Isso é uma história de custo contada como história de qualidade. Se eu estiver errado e alguma sobreviver ao custo com giro maior, a tese do capítulo ganha uma evidência que ele não apresentou. ⚠️ MEDIDO EM FOREX (EUR/USD e GBP/USD, diário agregado de 15m), e não em cripto. Isto é uma REPLICAÇÃO pré-registrada da mesma técnica no segundo mercado — não uma descoberta nova —, e a conta de múltiplos testes a trata como tal. O que muda em relação ao card de cripto: são 2 pares em 6,5 anos contra 540 em 9, o custo do giro é ~20× menor (spread de 1 pip cruzado uma vez, contra comissão de 0,1% por lado), o piso de detecção é ~10× menor (0,092% contra 0,97%) e NÃO há viés de sobrevivência, porque par de moeda não é deslistado. Previsão específica: com apenas 2 ativos, os episódios independentes vêm do TEMPO e não da variedade de ativos, então espero N efetivo baixo e uma proporção alta de INCONCLUSIVO — e o que for afirmado aqui vale mais que em cripto, porque o custo não tem como ser o coveiro.
Pre-registration exists to keep prediction apart from rationalisation: written after the number, every hypothesis is right.