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 exchange connects mean-variance portfolio choice to the CAPM decomposition of asset returns into market exposure and idiosyncratic residuals. Under the answer’s assumptions that residuals have zero mean and are mutually independent, the covariance matrix…
The document sets out a conditional factor model for the excess returns of multiple assets. At each observation time, an asset’s return is represented by a time-varying intercept, exposure to a set of common tradable factors, and an idiosyncratic noise term.…
The document asks whether a portfolio’s expected returns should use only statistically significant factors identified through Fama–MacBeth analysis or all factors in the model. The response distinguishes a statistical selection view, which would omit…
The document explains a practical use of Fama–French style factor models: assessing whether a stock or portfolio earns returns beyond those associated with established risk factors. It describes regressing the portfolio’s returns on the factors and…
The document explains two reasons to weight cross-sectional regressions when estimating factor returns in a fundamental factor model. The technical reason is to address heteroskedasticity: smaller companies’ returns may be more volatile than larger…
The document asks why adding regression residuals to asset returns can leave their covariance unchanged. In a factor model, return covariance separates into covariance explained by the shared factors and covariance between residuals. If residuals are…
The document explains how buying pressure can reduce an asset’s expected return when it is priced above the Security Market Line: stronger demand raises today’s price, lowering expected future return for a given expected payoff. The reverse applies to an…
The document considers how to test the claim that common market movements leave no meaningful stock-specific returns. It describes CAPM regressions, where significant average beta effects, near-zero intercepts, and smaller residual variation would be…
The document presents a Quantopian-style equity momentum factor formula and asks why it appears to assign a negative score when recent returns exceed longer-term returns. The calculation compares a price return measured from roughly one year earlier to a…
The document explains that the SMB series in the Fama–French three-factor and five-factor datasets differ because they are built from different portfolio sorts. The three-factor SMB uses size and book-to-market portfolios. The five-factor SMB combines size…
The document discusses how to set strategic weights across broad asset classes while overlaying separate tactical signals. The questioner seeks long-horizon allocations informed by economic and country views, rather than risk parity or mean-variance…
The document presents a proposed way to estimate historical alpha for a set of fund returns. The approach regresses each fund’s returns on excess returns for selected underlying exposures, interprets the fitted coefficients as factor betas, and treats…
The document clarifies that the classic Fama-French factors are formed through characteristic sorts rather than portfolio optimization. It outlines a size and book-to-market procedure: classify stocks into small or big groups using market capitalization,…
The document considers how to estimate expected returns for mean-variance portfolio optimization, noting that a simple historical average is a basic and potentially inadequate choice. It emphasizes that return estimates are difficult to make reliably because…
The question describes annual sorting of stocks into portfolios by ESG score, holding each portfolio for seven years, rebalancing annually, and regressing monthly returns on the Fama-French five factors plus momentum. The reported pattern is negative alpha…
The document raises a question about why stock return predictors may weaken after academic publication. It cites McLean and Pontiff’s reported evidence that portfolio returns were lower out of sample and declined further after papers describing predictors…
The note explains pricing errors in the Fama–MacBeth approach to evaluating a factor model, using the Fama–French five-factor model as context. In each period, a cross-sectional regression relates assets’ excess returns to their estimated factor exposures…
The document poses a mean-variance portfolio question involving the market excess return and two long-short factor portfolios. Transaction costs have already been deducted from the factors, leaving their expected net returns negative. Under these…
The document examines why stocks with higher idiosyncratic volatility have sometimes shown lower subsequent returns. It describes evidence that the relation weakens or disappears after accounting for MAX, the stock’s highest daily return in the prior month,…
The document considers how to interpret a strategy’s estimated alpha when it is not statistically significant, even if its estimate exceeds the alpha of an equally weighted comparison portfolio. It frames alpha as the intercept in a regression of excess…
The document considers whether hedge fund returns can be explained by static exposures to common investment factors. It warns that a high in-sample fit, such as a strong R-squared from a lasso regression, may be misleading when many candidate factors allow…
The document raises a model-fit question about two-stage Fama–MacBeth regressions using ten industry-sorted portfolios as dependent variables and the Fama–French three factors as explanatory returns. It reports that the value-weighted portfolios have an…
The document asks how evidence of higher average net returns for active equity strategies outside the United States can fit with Sharpe’s zero-sum argument for active management. The proposed explanations distinguish the investor groups and the performance…
The document outlines a starting point for hedging an equity portfolio with a factor risk model. First estimate the portfolio’s factor exposures, preferably from holdings according to the response, then compare them with a benchmark or index. The resulting…