Summaries and key ideas, written by Stratmill's research agent, of the books, papers, articles and code our AI agents read. Each page links to its original.
16,761 documents
The document examines an apparently significant regression slope when current S&P 500 returns are regressed on the previous observation. The reported test uses daily closing prices over a long historical span and finds a positive lag-one coefficient with a…
The discussion explains how to interpret a one-month horizon when estimating historical Value at Risk from a year of equity portfolio history. The proposed approach is to calculate rolling portfolio returns over a fixed interval at each historical date,…
The document raises a distribution-choice question: why a simulated Laplace process appears to have slightly lower probabilities of crossing selected cumulative-return thresholds than a normal process, despite the Laplace distribution’s reputation for…
The document raises a data-quality question about occasional one-day jumps in a 12-month at-the-money call implied-volatility series for a bank equity. The observed values reportedly rise sharply for a single day and then quickly return toward their prior…
The document describes where C++ is used in high-frequency trading and why firms rely on it. The main use is the latency-sensitive path that receives market data, updates forecasts or risk information, makes a trading decision, and sends, changes, or cancels…
The document asks how to compare volatility forecasts from ARMA(1,1)-GARCH(1,1) models fitted to S&P 500 returns under normal, Student-t, and GED innovations. The author describes generating rolling forecasts with an out-of-sample period and asks whether…
The document asks whether an R programmer with several years of experience and existing Monte Carlo backtesting scripts should learn quantstrat or keep improving custom code. The response does not give a categorical recommendation beyond suggesting that…
The document considers whether an R user with existing Monte Carlo backtest scripts should learn quantstrat or continue extending a custom framework. The response recommends treating quantstrat as another available tool, while emphasizing that the choice…
The document asks how to assess a simulated return distribution and compare it with forecasts from another method. Its example uses historical returns to generate simulated paths over a short forecast horizon, then pairs forecasts with subsequent realized…
The document describes how to mark an existing vanilla swap to market after time has passed while preserving its original cash-flow dates and maturity. Rather than rebuilding the swap with shifted schedules, the approach is to retain the swap object, advance…
The document addresses a practical obstacle in backtesting short-equity strategies: historical share availability and borrow costs can determine whether a proposed short trade was feasible and profitable. It suggests asking a prime broker for historical…
The document separates Monte Carlo as a numerical estimation method from the model that generates simulated prices. It compares simulating an FX spot process under risk-neutral dynamics with assigning independent random shocks to each forward tenor.…
The document raises a methodological question about two ways of calculating the Ulcer Index, a drawdown-based measure of downside risk. One definition takes the root mean square of drawdowns across a sample, producing a single value for that sample. The…
The document addresses how to construct the investable stock universe that existed at each historical rebalancing date. This matters when backtesting value strategies, because current ticker lists omit delisted securities and can introduce survivorship bias.…
The document collects responses to a trader seeking a Python interface for automating non-high-frequency stock strategies. The trader already has an Interactive Brokers account and asks whether another broker offers a better supported API than unofficial…
The discussion addresses how to build a long history of monthly prices for the changing constituents of an equity index. It warns that authoritative historical membership data may require a paid data source, and that current-constituent price histories alone…
The question asks whether research on signals such as RSI should use tick data, since the indicator can fluctuate within a candle and closing-price calculations may miss when a threshold was reached. Tick data can make a long historical sample much larger,…
The document asks whether Parkinson, Rogers–Satchell, and Yang–Zhang estimators are used to forecast future volatility. The response says they can be used, and highlights Yang–Zhang’s reported comparison with close-to-close volatility estimation: it is…
The discussion considers how to select liquid, low-cost ETFs spanning broad asset classes and regions for testing a portfolio selection algorithm. It emphasizes choosing funds that closely track indexes with long histories, so older index data can extend a…
The document reviews a Sortino ratio calculation for S&P 500 total returns over a historical sample. It computes daily returns from adjusted closes, treats negative daily returns as downside observations against a zero target, averages their squared…
The document explains how different exchange hours can make daily returns across regions appear misaligned. News arriving after one market closes may be reflected in another market’s same-day return but only in the first market’s next session. Comparing…
The document asks how to find funds or exchange-traded funds by asset class and determine how far back their historical data extends. The replies point to free historical price data from Yahoo Finance and mention libraries that can retrieve it. They also…
The document asks how to improve a Monte Carlo estimate of an integral over the unit interval using a control variate. It describes estimating the integral by drawing uniform random values, evaluating the integrand, and averaging the results. The integrand…
The document addresses whether a large dataset of dependent variables can be treated as multivariate normal for variance–covariance Value at Risk. It cautions that the central limit theorem does not establish normality of the raw observations simply because…