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 explains how to aggregate daily log returns into a weekly return and why the endpoints must match the intended holding period. Adding consecutive daily log returns telescopes: intermediate prices cancel, leaving the log price difference between…
The document discusses obtaining market capitalization for S&P 500 stocks on a historical date using low-cost data sources. Suggested approaches include extracting data with R, downloading data from a general-purpose service, or combining historical prices…
The discussion offers starting points and practical cautions for optimizing portfolios against value at risk (VaR). It recommends Euler capital allocation as an introduction, then describes a simulation approach: hold a large set of scenarios fixed and…
The document considers a European call in a three-period recombining binomial tree and asks how to price it efficiently by hand. It presents the risk-neutral valuation principle: discount the expected terminal payoff, using the binomial probability of each…
The document asks whether alternative component weighting schemes can improve a volatility index’s forecasts of realized volatility. The question describes a simple trade-weighted emerging-market index that was highly correlated with the VIX over a stated…
The document compares rolling and expanding estimation windows for GARCH volatility forecasts. A rolling window emphasizes recent observations, which may help when volatility shifts between regimes. An expanding window keeps the full history and may capture…
This exchange explains why buying when a short-term exponential moving average crosses above a longer-term average may appear effective on a chart but fail as a trading strategy. The main failure mode described is a market moving sideways rather than…
The document diagnoses a JavaScript implementation of an internal rate of return calculation using Newton’s method. It evaluates dated cash flows by discounting each amount according to its time from the initial date, then updates the rate using the ratio of…
The answer presents an empirical framework for comparing realized volatility measures when the latent true volatility is unobservable. It recommends specifying data cleaning, sampling frequency, candidate measures, a volatility proxy, and ranking and…
The document explains why feeding historical order-book updates into a fresh matching engine can produce cancellations or executions for orders the engine never saw. The underlying issue is incomplete initial state or limited market-by-order coverage: a data…
The document outlines a basic workflow for testing an equity strategy: encode it in a platform or record discretionary trades manually, optimize parameters on one portion of historical data, and evaluate the chosen approach on separate out-of-sample data.…
The document considers how to calculate a daily Sharpe ratio when a strategy is invested during only part of the measurement period. The accepted answer says to include zero returns for periods when the portfolio is not held, then calculate the daily Sharpe…
The document considers how to chart performance for a portfolio rebalanced quarterly when the input series contains daily log returns. It compares geometric and non-geometric settings in a performance summary and asks whether the non-geometric result…
The document asks whether the claim that the investing crowd is usually wrong can be made precise and tested. It sketches a simple definition of the crowd as the larger of two groups betting on whether an index will rise or fall over the next period. The…
The document considers a strategy that holds stocks for six months and rebalances monthly, evaluated through six staggered starting dates. It suggests combining the monthly performance streams and annualizing them, rather than averaging the separate compound…
The document compares two R backtesting options: Quantstrat, which works with related portfolio and financial-instrument packages, and the Systematic Investor Toolbox (SIT). It does not provide a formal benchmark; instead, it collects user impressions about…
The note addresses a non-finite initial-value error when estimating a Markov-switching vector autoregression in R. One answer suggests that the model may require stationary input and recommends removing trends, for example by subtracting a mean or a fitted…
The document discusses why risk managers and portfolio managers may handle extreme return observations differently. Retaining genuine extremes gives a more conservative view of realized risk, while robust estimates that reduce their influence may better…
The document asks whether historical evidence can show how profitable technical analysis is in practice. It calls for evaluation across multiple years and market conditions, with returns and loss sizes considered rather than signal hit rates alone. It also…
The document considers whether stock and bond histories can help extend the limited return records available for illiquid assets such as private equity, real estate, and hedge funds. It recommends first addressing serial correlation caused by appraisal…
The discussion considers how to compare two strategies with the same number of winning and losing trades when the order of outcomes differs. It explains that there is no single performance measure that captures every criterion; a trader can instead combine…
The discussion asks why a logistic regression strategy can show acceptable backtest and walk-forward performance even when its coefficients have insignificant p-values. It cautions that standard significance tests assume a single model was specified in…
The document discusses using Monte Carlo simulation to examine uncertain inputs in a financial model and the resulting range of business outcomes. Examples of inputs include product price, initial customer demand, growth, and market size; outputs include…
The document asks how to compare a quarterly regression of GDP changes on business investment changes with a regression using rolling five-year percentage changes. It observes that the rolling series produces a much higher adjusted fit, while raising concern…