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.
4,194 documents
The document examines why the German HML value factor can have a positive average return over a long sample yet a negative, statistically insignificant average in a later subperiod. A replication using German stock data reports a positive and significant HML…
The note explains the bias statistic used to assess portfolio risk forecasts in factor models. For each period, the method divides the realized portfolio return by its forecast volatility, then calculates the standard deviation of those standardized returns…
The document examines a workflow that estimates a covariance matrix from stock log returns, extracts principal components, and then projects log prices onto those components. Its central concern is that price levels are nonstationary, so the covariance…
The discussion considers why experienced human traders can earn money using familiar approaches such as pairs trading, trend following, and factor investing. It offers several possible explanations: chance can leave a visible group of winners, strategy…
The document raises implementation questions about using the Fama–French three-factor and five-factor models with monthly returns for large European companies. It asks whether a European risk-free benchmark, such as a German government bond yield, would be…
The document proposes a way to build a basic industry factor model for US equities when paid industry classifications are unavailable. Instead of assigning each stock a binary membership in a known industry, select liquid sector or industry ETFs that…
The document outlines a basic workflow for backtesting an equity selection strategy in MATLAB. It forms a portfolio by applying a characteristic-based selection rule to a matrix of asset returns, then computes portfolio returns by averaging the returns of…
The discussion separates three measures that can be confused when reading a valuation example: the price-to-earnings multiple, the price-to-book ratio, and return on equity. A market index value compared with book value gives a price-to-book ratio; it does…
The document asks whether quantitative finance can model markets without assuming martingale behavior. It frames the question around the view that martingales capture unpredictability and are associated with the efficient-market hypothesis, while exploitable…
This document is a curated reading list spanning factor investing, trading and execution, volatility estimation, derivatives pricing, and commodity futures. It names influential papers and briefly describes their contributions, including multifactor asset…
This note explains how redundant factor exposures make ordinary least squares attribution underdetermined. In its example, every Japanese stock has identical exposure to both a Japan country factor and a JPY currency factor, so the two columns of the…
The document asks whether combining multiple valuation measures, such as earnings multiples and dividend-discount estimates, can help time broad equity markets or forecast stock returns relative to fixed income. It also raises the possibility of combining…
The document frames a return-measurement choice for equity factor research using weekly prices across thousands of stocks and annual portfolio rebalancing. It contrasts the compounded simple return over the year with the sum of weekly log returns, and notes…
This discussion clarifies the difference between the CAPM relation among expected returns and beta, and a regression of realized returns through time. CAPM says that expected excess return is related to market beta; it does not assert that each period’s…
The document asks how differences in estimated asset betas affect a mean-variance optimal portfolio. The optimizer described minimizes portfolio variance subject to a target expected return and a fully invested constraint. In the standard formulation, the…
The discussion outlines a practical workflow for developing credit ratings or default-risk estimates from company fundamentals. First choose a target, such as observed defaults, agency ratings, or expert assessments, then assemble candidate financial…
Volatility timing adjusts exposure to risky assets according to recent or current volatility. The basic approach reduces exposure when measured volatility is high and increases it when volatility is low; the document notes that this can mean cutting risk…
The discussion considers how often to calibrate or rebalance equity factors built for research on the S&P. It gives a factor-specific answer: momentum may be calibrated daily, while slower-moving value measures may suit monthly calibration. This implies that…
The document compiles places to find quantitative research on equities, including sell-side bank research teams and investment strategy publications. It also points to independent research providers, academic or practitioner paper collections, research…
The response outlines a practical portfolio construction process for a large stock universe: screen holdings to a manageable set, estimate or model their covariance, impose linear portfolio constraints, and choose an objective that balances risk, alpha, and…
The document sets up a multivariate excess-return market model for several assets, with normally distributed, independent errors and a shared market excess return. It writes the likelihood and differentiates with respect to the intercept vector, yielding an…
The document surveys ways to turn value investing into measurable stock-selection signals. It lists valuation measures such as dividend yield, earnings yield, price-to-book, return on equity, and accrual-based earnings quality, alongside related signals…
The document examines why investors might avoid equity factor portfolios despite reported historical premiums. It groups the main explanations into four possibilities: apparent returns may be data-mined or overstated; mispricing may fade as investors learn;…
The document examines the standard error calculation for second-stage coefficients in a Fama–MacBeth regression. It gives the estimator based on the dispersion of period-by-period coefficient estimates around their average, scaled by the square of the number…