Stats

A study of stock market gaps used data from a repaired source, which is a website that provides stock market information. The data covered the period from September 2020 to September 18, 2026, and included 1518 observations. The study used hypothetical one-share entry dollars with weights of 67.37 and 64.63. The results showed a correlation of 0.22817876236373233 between gaps, with the worst joint gap loss being $-4.97832962124513 on April 7, 2025. The study also found that the recent negative correlation is not a reliable way to reduce risk. A previous study that included the 2020 market crash had larger losses, but this study started in September 2020 and did not include the crash, which is why the worst loss was smaller. The study did not provide information on win rate, slippage, or half Kelly, and it was recommended not to make estimates or resize the data.

The analysis of PSIX is based on two premises. First, the daily adjusted returns of PSIX and other stocks, including ETN, POWL, NVT, and SPY, from December 27, 2024, to September 18, 2026, are available at https://runway.adityaperswal.workers.dev/data/stock-bars?symbols=PSIX,ETN,POWL,NVT,SPY&timeframe=1Day&feed=sip&adjustment=all. Second, the total return of PSIX is 55.5443%, and if the best and worst 5 days are removed, the returns become -40.3676% and 628.9994%, respectively. The best 5 days account for 217.025% of the net log gain. This symmetric deletion is a descriptive stress test, not a feasible trading strategy or a reason to avoid investing in PSIX due to its fat-tail nature, which refers to a distribution with extreme values. The mean daily return is 0.32275%, the median daily return is -0.34725%, and the 1st and 99th percentiles are -17.5354% and 19.0215%, respectively. An ordinary least squares regression, or OLS, which is a method to estimate the relationship between variables, was performed with the SPY index and an equal weight of ETN, POWL, and NVT. The results show an intercept of 0.065405% per day, a market beta of 1.37135, and a power beta of 0.83742, with an R-squared of 0.27974. However, the presence of correlated factors and selected survivors, which are stocks that have survived a certain criteria, precludes causal alpha, or the ability to generate excess returns. The natural exit in 2025 had a mean return of 23.6247%, with a 95% confidence interval of -2.3439 to 49.5933, and in 2026, the mean return was -1.9832%, with a confidence interval of -15.9065 to 24.5858. These wide intervals indicate that the bootstrap method, which is a statistical technique to estimate the distribution of a parameter, cannot recover missing crises. In conclusion, tail dependence is expected, but the regimes and few trades cannot calibrate this entry, meaning that the analysis cannot accurately predict the behavior of PSIX due to its complex nature.

A study of BlackBerry's earnings releases from June 2023 to June 2026 found that the median absolute close reaction was 9.1152815% and the 80th percentile was 12.832986%. The study used adjusted SIP bars to measure reactions to morning and evening release calls. The median reaction for the training period from 2011 to 2025 was 9.1153% and the 80th percentile was 12.6829%. The chronological holdout for 2026 had two reactions of +8.2153% and +19.9536%. A bootstrap analysis with 20,000 iterations and a seed of 91906 found that the 95% intervals for the median were 6.9860% to 12.6829% and for the 80th percentile were 10.0756% to 22.2767%. On September 18, the stock price was $7.99 and the put option bid was $0.06 and ask was $0.20, with a full premium of $20 and an expiry of 8 days after the September 24 issuer event. The hurdle rate was 14.893617% and the hypothetical put option downside intrinsic value was $0.03535558, which was 0.1767779 times the premium. Both gates failed, meaning that the absolute upward move could not pay for the put option. No affordable contract was found in the 230 retrieved snapshots from October 1 to November 6. The source of the data was https://runway.adityaperswal.workers.dev/data/option-chain/BB?feed=indicative. The price ceilings for the same stock price were negative for the $7 put option, $0.238311 for the $7.5 put option, and $0.133839 for the $8 put option, indicating that a potential nearer strike was only possible if the fresh price fell below the ceiling. Statistical eligibility is not the same as actual option expectancy, and there was no cash-pressure override.

The analysis is based on two premises. First, it uses the same split-normalized SIP series as the signal table, which can be found at https://runway.adityaperswal.workers.dev/data/stock-bars?timeframe=1Day&feed=sip&adjustment=all&start=2020-09-01&end=2026-09-18T23:59:59Z. Second, the 90th percentile of 1255 overlapping 60-session returns from September 20, 2021, to September 18, 2026, is 10.71796% for EEM and 20.62795% for XLE. The autocorrelation of adjacent gains is 0.97286 and 0.97481, which means the 1255 observations are not independent trials. When looking at every 60th endpoint, there are 20-21 observations per phase. The range of the 90th percentile for EEM is 7.5403-14.4586% with a median of 10.1740%, and for XLE it is 12.3929-24.9686% with a median of 19.5529%. The phases are mutually dependent and the range is not a confidence interval. From 2021 to 2023, there were 574 observations, and from 2024 to 2026, there were 681 observations. For EEM, the 90th percentile increased from 6.2663% to 12.1418%, the median increased from -2.8085% to 5.2833%, and the percentage of positive observations increased from 32.9268% to 85.7562%. For XLE, the 90th percentile decreased from 23.0071% to 17.3154%, the median decreased from 7.1487% to 2.6234%, and the percentage of positive observations increased from 63.5889% to 64.3172%. The conclusion is that the historical upside threshold is sensitive to the time period and is not a 90% probability target. There is no claim that the strategy was retested or held out, and the known regimes are descriptive. The data is constrained by survivorship and dividend completeness. A counterexample is that a sustained new regime can shift the next 60-day distribution entirely, so it is recommended to keep a mandated 5-year window and a one-share size rather than optimizing the target to a favorable phase.

The relationship between different sectors of the stock market has changed significantly over time. This is based on two premises: first, daily returns from September 18 were used, with some adjustments made to ensure the data was consistent. Second, the current selection of stocks was chosen after the fact, which may introduce some bias into the results. The analysis compared two time periods: a five-year sample with 1255 data points and a more recent sample with 179 data points. The results showed that the correlation between different sectors, such as technology (XLK), energy (XLE), and healthcare (XLV), was different in the two time periods. For example, in the five-year sample, the correlation between XLK and XLE was 0.241529, while in the recent sample it was -0.247776. The analysis also looked at the volatility of each sector, with results including an annual volatility of 0.2597661336235835 for XLK in the five-year sample and 0.2835588873548983 in the recent sample. The conclusion is that the recent negative correlations between sectors cannot be relied upon to continue, and that the volatility of a basket of stocks with equal daily returns is not the same as the actual profit and loss of an investment strategy. The analysis did not claim to have found a way to predict future results, and the 2026 data was not used as a separate test of the strategy after it had already been researched.

A study of daily stock returns from 2026 through September 18 found the following: the daily adjusted simple returns for OCC, GLW, and SPY stocks were analyzed. The correlation between OCC and GLW was 0.481718, and between OCC and SPY was 0.199248. A statistical method called Ordinary Least Squares, or OLS, was used to analyze the relationship between OCC and SPY, which found an intercept of 0.869058% and a beta of 2.059435, with an R-squared value of 0.039700. The daily return percentiles for OCC were -13.2705% at the 1st percentile, -10.4709% at the 5th percentile, -0.28454% at the 50th percentile, 14.8018% at the 95th percentile, and 28.6742% at the 99th percentile. This means that OCC's returns are highly dispersed, with a positive mean and intercept, but a negative median and a fat positive tail. The study concludes that the relationship between OCC and its suppliers, such as GLW, is not a reliable indicator of future returns, and that the correlation between OCC and GLW is not strong enough to establish a causal link. The study also notes that GLW and OCC are partly correlated exposures, not independent positions, and that no significant or stationary relationship was found.

A news scan found the headline 'R91904 SFIX ten-event distribution: affordable put fails ask, passes only near.13'. This refers to a study of the stock SFIX. The study is based on three main ideas: first, it looks at ten events related to AMC earnings from March 2024 to June 2026; second, it measures how the stock price changes from the day before an event to the day after; and third, it uses a specific method to adjust for daily changes. The study found that on September 18, the price of a put option, which is a type of financial contract, was.28. A put option is a contract that gives the buyer the right to sell a stock at a certain price. The study calculated that the median, or middle value, of price changes was 16.578014%, and the 80th percentile, or the value below which 80% of the data falls, was 31.413933%. The study concluded that the current price of the put option is too high and that it would be better to wait for a cheaper price. The study also found that only one out of ten events had a price change that exceeded the cost of the put option, and that the mean, or average, price change was.116659. The study used a method called bootstrapping to estimate the range of possible price changes, and found that the 95% confidence interval, or the range of values within which the true value is likely to fall, was 7.990075% to 30.251626% for the median, and 16.524823% to 44.347826% for the 80th percentile. The study also noted that the results are limited by the assumption that the data is independent and identically distributed, and that the soundness of the results has not been proven. The data used in the study can be found at https://runway.adityaperswal.workers.dev/data/option-chain/SFIX?feed=indicative and https://runway.adityaperswal.workers.dev/data/stock-bars.

The overnight diversification strategy, known as a way to reduce risk by spreading investments, failed a test of stability over a long period of time. This test was based on three main ideas: first, the difference between the previous day's close and the next day's open is used as a proxy for overnight price changes, not the actual path of prices during the night; second, some missing data for the XLE stock was fixed using information from the issuer; and third, the test compared price gaps due to stock splits with overall economic return gaps. The test used daily stock price data from January 1, 2019, to September 18, 2026, for the EEM and XLE stocks. The results showed a correlation of 0.46018 between the two stocks' price gaps over the entire period, but this correlation was much lower over the most recent period, at -0.40937. There were 28 instances of simultaneous gaps below -2% out of 1938 total gaps. In the 97 instances where EEM had one of its worst 5% gaps, XLE was also negative 68.04% of the time. The worst joint gap was on March 16, 2020, with a scaled exposure of 16.23047. These results support the idea that diversification between these two stocks may not be stable, but they do not predict what will happen in the future. The test has limitations due to the use of daily proxies and potential vendor revisions, but the conclusion is that there should not be an increase in investment size based on diversification, and it does not recommend withdrawing from the current investment strategy.

A question was asked about the stability of a specific financial measurement, called the 5-year rolling 60-session P90, which is a historical return measure. This measure is based on certain premises, including the use of adjusted data from a source called SIP, which is normalized, meaning it is adjusted to a standard scale. The data is split into sections, with 1,255 endpoints per ETF, and the normalization details are specified. The P90 measure is calculated for three ETFs, XLK, XLE, and XLV, and the results are 18.3622%, 20.6279%, and 10.6286% respectively. The correlations between adjacent windows of data are also calculated, with results of 0.97755, 0.97481, and 0.97676. The data is then divided into 60 non-overlapping sections, each containing 20-21 observations, and the P90 measure is calculated for each section. The results show that the P90 measure varies widely, from 12.983% to 27.164% for XLK, 12.393% to 24.969% for XLE, and 7.040% to 12.423% for XLV. The data is not independent, meaning that the sections are not completely separate from each other. When the data is divided into two chronological halves, the P90 measure is 17.105% and 22.554% for XLK, 22.269% and 18.233% for XLE, and 9.515% and 11.698% for XLV. It was found that 73 out of 126 upper-decile endpoints for XLE fell in 2022, and removing that year from the data lowers the P90 measure to 17.5194%. The conclusion is that the historical quantile, a measure of the range of possible returns, is reproducible, but the estimated precision is weak and dependent on the specific regime, or market conditions. One counterargument is that the width of the interval is due to the deliberate overlapping of the estimator and the small disjoint samples, but this does not necessarily invalidate the fixed rotation premium, a measure of the excess return of a portfolio. The validity of the results is limited by the dependence of the data, which reduces the unique information, but does not automatically introduce systematic bias. The soundness of the results is also limited by the single 5-year vintage, the ex-post current leaders, the split/dividend methodology, and the unobserved future regimes. A news scan found the headline that no new strategy backtest, out-of-sample edge claim, Kelly odds, or target override is made. The sources stop changing this descriptive answer after chronology, offsets, leave-year-out, and block-length checks. A new independent total-return index or corrected corporate-action feed could alter the exact numbers, but the targets would be retained by a fixed rule.

A news scan found the headline 'Weekend gap tails versus ordinary overnights: joint risk is real, mean penalty uncertain'. This refers to a study of stock market gaps, which are differences between the closing price of a stock on one day and its opening price the next day, a concept known as a gap. The study looked at gaps in the prices of certain stocks, specifically EEM, QQQ, and IWM, over a period of time from September 2021 to September 2026. It found that weekend gaps were worse than ordinary overnight gaps, with a joint negative return of 31.1538% for weekends compared to 28.2653% for ordinary nights. The study also found that the correlations between the gaps in these stocks were high, with a correlation of 0.716731 between EEM and QQQ, 0.653395 between EEM and IWM, and 0.826848 between QQQ and IWM. The largest joint gap occurred on August 5, 2024, with EEM falling 5.25918%, QQQ falling 5.35702%, and IWM falling 5.27219%. The study concluded that while weekend gaps were worse, there was no established mean penalty or future bound, meaning that it is unclear whether these gaps will result in long-term losses. The study also noted that the worst individual gap for EEM occurred on an ordinary day, March 3, 2026, with a loss of 5.73717%. The data for this study came from https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all.

The automated trading fund manager made some observations about certain stocks. They looked at the daily returns of these stocks from February 6 to September 18, 2026, and found some connections between them. Specifically, they found that the correlation, which measures how much two things move together, between GLW and MU was 0.5976, between GLW and FPS was 0.5541, and between FPS and BTDR was 0.5052. They also used a statistical method called ordinary least squares, or OLS, to estimate the beta, which measures how much a stock moves compared to the overall market, of each stock. The betas were 3.254 for GLW, 3.387 for FPS, and 4.412 for BTDR. However, the manager notes that these findings are not conclusive and may be influenced by the fact that they were looking for connections after hearing about artificial intelligence, or AI, narratives. The manager concludes that stocks in the glass, switchgear, and computing industries may be related in terms of risk, despite having different supply chain issues. This means that if the manager decides to invest in these stocks in the future, they will need to consider their combined risk, rather than treating each investment as a separate bet. The manager also notes that unexpected events, such as funding or production shocks, can overwhelm the average correlation between these stocks. Currently, the manager does not have a position or plan to make a trade in these stocks.

A news scan found the text describing payoff distributions for a trading fund. The fund used a method called bootstrap draws, which is a way to estimate how well a trading strategy works. The results showed that for the stock GLW, the average payoff was 0.322% per trade, with a 95% confidence interval of -2.004% to 2.870%, and a win rate of 33.33%. The average win was 10.22% and the average loss was 4.63%. For the holdout set, which is a group of trades not used to train the model, the average payoff was 4.557%, with a confidence interval of 0.090% to 9.335%, and a win rate of 56.25%. The average win was 12.00% and the average loss was 5.01%. The fund also tested other stocks, including OCC, BTDR, FEAM, FCEL, and MU. The results for these stocks were mixed, with some showing positive payoffs and others showing negative payoffs. The fund used data from a source called stock-bars, which provides historical stock prices. The results are based on certain assumptions, including that the trades are independent and identically distributed, and that the companies chosen are still in business. The results are not proof of a current trading edge, but rather evidence that can be used to investigate further. A countercase is that new contracts or scales can improve future cash flows despite historic losses.

The past daily returns of EEM and XLE, adjusted for certain factors, show how their prices have spread out in the past, but this does not guarantee their future performance. According to data from https://runway.adityaperswal.workers.dev, which covers the period up to September 18, 2026, the returns of EEM and XLE have been analyzed. The analysis uses a fixed target based on five-calendar-year ending dates and 1255 overlapping 60-session gains, finding that the 90th percentile return for EEM is 10.71796349% and for XLE is 20.63484442%. Looking at the last 1260 sessions, which include five earlier observations, the 10th percentile, median, and 90th percentile returns for EEM are -8.1723%, 2.3230%, and 10.7033%, respectively, and for XLE are -6.6200%, 3.8107%, and 20.5424%, respectively. The daily correlation between EEM and XLE over 252 days is -0.159464, but over 1260 days it is 0.252817, indicating that the current low correlation may not be a reliable form of insurance against losses. The annualized daily volatility for EEM and XLE is 19.9155% and 25.6825%, respectively. However, in the event of a global liquidation, both correlations could turn positive and prices could gap through stop-loss levels. Therefore, the conclusion is to retain two distinct exposures to EEM and XLE, with a whole-share minimum sizing, and not to use diversification-based leverage or double the position.

The fund manager made some assumptions to analyze a basket of investments. They chose the top 3 investments, which are EEM, QQQ, and IWM, and gave each the same weight of 93.33%. They looked at the daily returns of these investments over 252 days and found that they are highly correlated, meaning they tend to move together, with correlation values of 0.831269, 0.690365, and 0.739377. On 74 out of 252 days, all three investments had negative returns. The worst loss over a day was 13.874044% and the 99th percentile loss was 8.254056%. This analysis is based on past performance and does not guarantee future results. The fact that these investments are from different parts of the world does not mean they are independent of each other, as they can still be affected by the same global events. The data for this analysis came from the website https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all. The fund manager has not yet measured the performance of this strategy in real-time or determined its win rate or optimal betting size, also known as Kelly calibration, as there are no live trades recorded in their ledger.

The relationship between selected stocks in a basket has not changed. The analysis is based on adjusted stock prices through September 18, and the current basket was chosen after the fact. The daily return statistics are used to describe the stocks, not as a strategy for investing. A correlation, which measures how closely stocks move together, was calculated over 60 and 252-day periods. The results show that the stocks tend to move in opposite directions, with correlations ranging from -0.46584 to 1. However, even with this negative correlation, the worst simultaneous daily return for the basket was -7.0913% and the 1st percentile was -2.7520%. This means that having stocks with negative correlations does not necessarily reduce the risk of large losses, known as gap stress. The analysis is limited because it only looks at past data, which may not reflect future market conditions. Additionally, the 1331 observations used in the analysis are not independent of each other, but rather are dependent on the specific market conditions at the time. Since there are no live trades, it is not possible to estimate how much the actual performance of the strategy would differ from the expected performance, known as slippage, or the percentage of winning trades, known as the win rate.

A fund manager analyzed the performance of two stocks, NVT and HUBB. The analysis used a method called bootstrap, which is a way to estimate how reliable the results are, and found that NVT had a higher average return per trade, 3.036%, compared to HUBB, which had a negative return of 21.13% in the holdout period. The holdout period is a time frame used to test the performance of a strategy, separate from the time frame used to train it. The results also showed that NVT had a higher win rate, 44.44%, and a higher average win, 13.558%, compared to HUBB. However, the analysis noted that the results are limited by the lack of precision and the reliance on a single ledger, which is a record of all transactions. The analysis also found that two trades, FRO and STNG, were winners, but there was no stop or target exit, which is a price level at which to sell a stock, and therefore, the strategy's stop probability, average losing trade, or execution slippage, which is the difference between the expected price and the actual price, could not be estimated. The data used for the analysis was from September 2-4, after a reset, which is a restart of the system. The analysis concluded that NVT merits a prospective signal and cash monitor, but statistical confidence alone is not enough to authorize entry into a trade, and other factors, such as a missing trigger and current target economics, control the decision.

The manager of an automated trading fund made some observations about the recent performance of a selected basket of stocks. The manager looked at the daily returns of the stocks in the basket, with each stock having an equal weight. The manager also calculated the correlations between the stocks, which is a measure of how much they tend to move together. The correlations were negative over the past 60 and 252 days, meaning that when one stock went down, the others tended to go up. However, the manager found that on the worst historical day for the basket, the correlations turned positive, meaning that all the stocks went down together. This challenges the idea that diversification can always protect against losses. The manager also found that the worst historical day for the basket was a loss of 7.0913%, which would translate to a loss of about $22.70 at the current exposure level of $320.10. The manager concludes that increasing the risk size of the portfolio in an attempt to diversify it would not be a good idea. The manager also notes that the leadership of the stocks in the basket has been confirmed, but the breadth of the market has deteriorated, and would consider changing the initial candidates if the eligibility criteria changed, but not because of any change in the overall market narrative.

The automated trading fund manager made some premises. They chose three equity ETFs. The returns of these ETFs are aligned on common days. The sizes of the ETFs are hypothetical, not based on historical data. Over 252 sessions, the Pearson correlation between EEM and QQQ was 0.831269, between EEM and IWM was 0.690365, and between QQQ and IWM was 0.739377. All three had negative returns on 74 out of 252 days. The current static basket has a daily loss of 8.159653 at the 1% quantile and a worst loss of 13.786708. On Friday, the hypothetical close-to-close profit and loss was +0.424213, which is not the missed executable intraday profit. IWM had a return of -0.465964% on Friday, -4.307993% over 20 days, and is 3.871641% above its Simple Moving Average, or SMA, which is a calculation to find the average price of a stock over a certain period. QQQ had a return of +0.631870% on Friday, +1.479752% over 20 days, and is 9.017802% above its SMA. EEM had a return of +0.179345% on Friday, +0.615431% over 20 days, and is 7.953498% above its SMA. This is a counterexample, meaning it is an exception to the general rule, and correlations may rise in a crisis and daily closes may conceal stop overshoot, which is when a stock price moves past a stop-loss order. The selection of these ETFs is based on hindsight, which means looking back at past data, and does not allow for strategy win-rate or Kelly inference, which is a way to measure the performance of a strategy. There are no closed trades, so the expectancy, or expected return, and slippage, or the difference between the expected and actual price of a trade, are unmeasurable. The specific mandate validation has already been done, and there will be no repeat backtest, which is a test of a strategy using historical data, or discretionary short-term signal veto, which is when a trader overrides a signal to buy or sell. The source of the data is https://runway.adityaperswal.workers.dev/data/stock-bars?feed=sip&adjustment=all, which is a website that provides stock market data.

A news scan found the report titled R91808 canal denominators, which states that there is no queue growth identifiable from monthly averages. The report includes the following points: 1. The DirectACP Sep10 AugustA34 report, available at https://pancanal.com/wp-content/uploads/2026/09/adv-34-2026-monthly-canal-operations-summary-august-2026.pdf, shows that the monthly total was 1029, with 33.19 transits per day and 33.1 arrivals per day. 2. A Python analysis found that the water-minus-transit time was 23.63 hours, which is 67.7077% of 34.90 hours, but this includes all non-transit time and not just congestion wait time. The rounded arrivals minus departures was -0.09 per day, which does not establish an actual queue change. 3. The report also found that 175 out of 178 Neo booked slots were used, which is 98.3146%, and 204 out of 227 auction slots were used, which is 89.8678%. However, Neo excludes auctions, so adding these percentages would double count and change the denominator. The physical capacity of 33.19 per day out of a sustainable combined capacity of 36-38 implies an utilization range of 87.34-92.19%. 4. The report concludes that prior constraints can raise freight, but the evidence weakens the inference of accelerating queue from headline booking fill. It also notes that concentrated Neo arrival waves can produce queues despite balanced monthly totals, and that daily class-specific arrivals, wait distribution, auction prices, and paid TCE are needed before calibrating stock edge.

The source https://runway.adityaperswal.workers.dev/data/stock-bars SIP/all Jan2016-Sep17 shows that TEN has 2691 daily gaps and none are less than or equal to -30%. The worst gap was -9.5963% on April 29, 2020, and the worst pre-2024 close return was -17.58995%. This does not mean there is no risk of a future disaster. Using a simple model, the daily upper limit is 11.1262%, which is 6.46126% over 60 sessions. A 5% probability per trade cannot be directly compared to a daily frequency, and crisis regimes can happen in groups, which undermines the simple model. So, the earlier 5%/-30% remains a stress case, not a calibrated probability, and the absence of such an event does not refute it. PSIX had an actual adjusted gap of -34.18735% on May 12, 2026, and -29.99754% on November 7, 2025. LPG had a worst pre-2024 gap of -22.27513%. The AA feed on November 1, 2016, showed an apparent -74.35646% gap, which was due to a corporate separation, as confirmed by https://investors.alcoa.com/resources/investor-faqs/default.aspx. If we start the current AA history from November 1, 2016, the clean worst gap is approximately -13.2465%. The correlation between TEN and other stocks is: TEN/FRO is 0.819413, TEN/STNG is 0.708182, and TEN/LPG is 0.600194. This means that the holdings would share a shipping factor, not independent bets. The conclusion is to retire the uncalibrated tail veto while keeping explicit gap sizing and regime uncertainty. The sample of closed trades cannot estimate the edge. The hard account risk and fund 101.99 cap remain, and there is no forced entry from removing an invalid inference.

A news scan found the text of a chronological risk-model audit. The audit is based on three premises: the current sizes of EEM, QQQ, and IWM, which are 89.95, 103.11, and 83.46, determine the fixed dollar daily return exposure; the adjusted close returns from 2016 to September 2017 and 2026 are aligned; and the model decay is 0.94, which was fixed before this computation. The standardized loss at the 99th percentile was estimated from 2016 to 2024 after 252 warm-up observations. The test period is from January 2, 2025, to September 17, 2026, which is 428 days, and the training period is 2263 days. The prior-day exponentially weighted moving average, or EWMA, squared return forecasts the next-day scale. The test data updates volatility only after realization, and the threshold multiplier is 3.015193607. There were four exceedances out of 428 days, which is 0.934579%. The latest next-day threshold is 8.343642 USD. This audit is a chronological risk calibration, not an independent out-of-sample, or OOS, strategy validation. The symbols and weights were chosen with hindsight, and prior runs already saw historical data. No selection, rebalancing, exits, or fees were modeled. No tuning sweep or gate was imposed. The pair correlations for EEM-QQQ, EEM-IWM, and QQQ-IWM are 0.719423, 0.689657, and 0.756580 for the training period, and 0.772195, 0.682891, and 0.802395 for the test period. The last 60 days had correlations of 0.832760, 0.634451, and 0.711276. The downside 189 days conditional correlations are 0.578614, 0.393634, and 0.642452, subject to selection conditioning. The test actual joint daily standard deviation is 3.530578, versus 2.239607 for independence. Ignoring dependence understates dispersion. The historical test worst dollar daily loss was 15.128603 on April 4, 2025, and the empirical value at risk, or VaR, at 99% is 9.368118, and the expected shortfall, or ES, at 95% is 7.609460. The dollar returns assume daily constant exposure for a risk lens, not buy-and-hold net asset value, or NAV. The valid conclusion is to retain dependence-aware stress sizing, not per-lot loss interpreted as book loss. The soundness limits one provider, revised history, daily closes miss exit delays and tails, and there is no confidence that 99% of future losses will stay below the threshold. The source is https://runway.adityaperswal.workers.dev/data/stock-bars, and the results are reproducible with quant.py and quant_results.json.

A review of the R91806 trading strategy found that its premises were not accurate. The strategy assumed a 5% probability of a 30% loss, which gave a conditional mean of 1.4467783586% and a breakeven point of 4.60072044%. However, there was no data to support this 5% assumption. The trading history only had two winning trades with no independent samples of losses. Adding a potential large loss to the historical returns could double-count the risk. Therefore, the strategy's use of this scenario as a hard veto is being superseded. It will be retained as a sensitivity test, labeled as such, and used alongside other empirical data and stress tests. The correction is to the model, not a signal to chase trades. The current frozen prices of 52.81, 45.41, and 55.36 still yield a low return of 0.31453R. The data source is https://runway.adityaperswal.workers.dev/data/stock-bars, and new panel data from September 17, 2016, is being analyzed, with results pending.

A news scan found the report from https://runway.adityaperswal.workers.dev/data/stock-bars. This report looks at how well a trading model works by checking its performance over two time periods: June 2021 to December 2024 with 902 gaps per ETF, and January 2025 to September 17, 2026, with 428 gaps per ETF. The report uses something called a retrospective chronological split, which means it looks back at how the model performed over these two time periods. It also uses a freeze pre-2025 stress, which is a way to measure the maximum possible loss, set at 10% for XLE and XLV, and 12.51854% for XLK. The report found that in the later time period, there were no breaches, or times when the model's performance was worse than the set stress level, for any of the ETFs. However, the worst performance for XLE increased from 4.952927% to 5.792734%, for XLV it increased from 1.975372% to 2.644903%, and for XLK it decreased from 6.259270% to 4.795771%. The full figures are: XLE had 902 training samples and 428 test samples, with a minimum loss of -0.049529267294310286 in the training period and -0.0579273396952954 in the test period, and no breaches; XLK had 902 training samples and 428 test samples, with a minimum loss of -0.06259270246217741 in the training period and -0.04795771263815474 in the test period, and no breaches; XLV had 902 training samples and 428 test samples, with a minimum loss of -0.01975371985633656 in the training period and -0.02644902894279455 in the test period, and no breaches. The report notes that the model only looks at gaps between the open and previous adjusted close, so it does not account for intraday price movements or unexpected events. The ETFs were selected based on current data, and the report concludes that just because there were no observed breaches, it does not mean that the model will always perform well. This diagnostic is not a guarantee of future performance, and the model should maintain its established stress levels and equal weights.

A trading fund manager made some notes about buying and selling stocks. The manager looked at the history of the stocks from 2016 to September 2017 and from 2020 to February 18, 2020, to April 15, 2020. The manager used a special formula to decide how much to buy or sell, which included a 50 basis point friction assumption, meaning a 0.5% cost. The formula also included a variable called g, which is the maximum of the daily adverse open gap and the adverse first two 15-minute lows relative to the prior close. The manager chose to buy and sell the following stocks: QQQ, IWM, and EEM. For each stock, the manager calculated the stress, stop, target, and gain. The stress is a measure of how much the stock price might drop, the stop is the price at which the manager would sell the stock to limit losses, the target is the price at which the manager hopes to sell the stock for a profit, and the gain is the potential profit. The manager also calculated the normal size of the trade and the size with a 3% equity budget. The manager found that the combined stress of the three stocks was 74.99695, which is 8.823% of the equity, and the normal stop was 6.88904, with a target gain of 37.02158 before costs. The manager used data from the website https://runway.adityaperswal.workers.dev/data/stock-bars to make these calculations. The manager noted that this is just a sizing analysis and not a backtest of the strategy or a calibrated live odds/Kelly analysis.

A source from https://runway.adityaperswal.workers.dev/data/stock-bars found the following daily correlations between sectors from June 2021 to September 17, 2026: energy and technology had a correlation of 0.238174, energy and health had a correlation of 0.241805, and technology and health had a correlation of 0.389758. All of these correlations are positive, which means that sector diversification does not remove exposure to the overall equity market. P90 targets refer to the historical 60-session quantiles with overlapping samples, and do not represent a 90% success probability. The gross target to risk ratios at the last close were approximately 5.17, 5.51, and 3.96. Since there is no trade history, the realized win rate, slippage, and conditional expected payoff are unknown. The published premium is accepted as per the mandate, and the correlations and bootstrap only describe exposure.