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 compares Fama–MacBeth regressions with a single panel regression whose standard errors are clustered by date, in the setting of financial data with cross-sectional correlation. Both approaches can address contemporaneous dependence under…
The discussion addresses how to use principal component analysis for relative-value analysis when interest rate levels are nonstationary. One proposed method applies PCA to daily rate changes, cumulatively sums the resulting factors, and regresses rate…
The document compares two empirical approaches for studying whether one stock characteristic explains returns or another variable. Double sorts group stocks by one characteristic and then sort within those groups by a second. This nonparametric approach…
The document surveys several ways to detect whether a systematic strategy’s edge is weakening. One approach tracks the information coefficient, the correlation between predicted returns and subsequent benchmark returns, and tests whether it remains…
The document explains how to interpret a stock regression’s loadings on the Fama-French size (SMB) and value (HML) factors. A negative SMB loading suggests exposure associated with larger-cap stocks, while a positive HML loading indicates value exposure. A…
The document sets up two asset returns driven by a common factor with opposite loadings, plus uncorrelated residuals of equal variance. It then defines one portfolio as the first asset and another as a weighted combination of both, with the weight tied to…
The discussion distinguishes Barra multiple-factor models from models intended to explain expected asset returns. Barra models are presented primarily as tools for decomposing the realized variation and covariance of returns across groups of securities, and…
The discussion distinguishes risk models, which explain return variation and support covariance estimation and hedging, from alpha models, which seek to forecast expected returns. Risk models can use a relatively small set of factors to estimate a large…
The document explains why a return model separates expected return from unexpected shocks, and how a single-factor model splits those shocks into a shared macroeconomic component and a security-specific component. Since expected return is a constant in this…
The document discusses how to evaluate a stock-sorting strategy whose portfolio returns appear to have different Fama–French three-factor alphas. It recommends using Newey–West standard errors to account for autocorrelation and heteroskedasticity, and…
The document considers whether monthly data for a small set of Swedish stocks can support Fama-French portfolio construction and regression. It warns that sorting a limited universe by characteristics may leave only one or two stocks in some portfolios,…
The document explains how to relate principal components back to the original variables after principal component analysis. Once eigenvalues identify components that account for a chosen share of total variance, the entries of each corresponding eigenvector…
The document derives a two-variable single-factor model from regressions in which both variables share a common factor and each has an idiosyncratic error. The derivation requires equal factor loadings and equal residual coefficients for the two variables.…
The document examines a return attribution regression that includes an intercept, country dummy variables, industry dummy variables, and factor exposures. Country and industry indicators can be linearly dependent, making the design matrix rank deficient and…
The document asks how to extend a standard CAPM regression to include squared and cubed market excess returns, which are intended to capture exposure associated with higher moments. The answer confirms that these terms can be included as additional…
The document asks how to measure crowding in factor strategies using evidence beyond trading volume and fund manager surveys. The questioner has tried Sharpe ratios and dividend revision rates, but reports that these have only produced rough screening…
The document raises two methodological questions about time-series regressions in the Fama–French asset-pricing framework. First, it asks why the method is called a time-series regression when estimation uses ordinary least squares. Second, it questions…
The discussion surveys ways to rank candidate variables for factor models when correlation among inputs is not the main concern. Suggested measures include rank correlation, causal or cointegration tests, information ratios, regression fit, premium…
The document surveys several ways to quantify earnings surprises when raw earnings levels are not comparable across companies and simple percentage changes can behave poorly around negative earnings. One approach measures announcement-window stock…
The document asks how to adapt a quadratic formulation of the maximum-Sharpe tangency portfolio to a factor model. Its proposed approach is to first convert factor-level inputs into security-level inputs, then apply the existing portfolio optimization…
The document asks how a study assessed whether small-cap and large-cap Sharpe ratios differed, after a simple calculation using the Sharpe difference multiplied by the square root of the observation count produced large p-values. The question presents…
The document explains how to read Fama–MacBeth cross-sectional return regressions in a study of gross profitability. The reported coefficients use monthly stock returns and describe the association between a one-unit change in a characteristic and subsequent…
A portfolio sort groups assets by a characteristic, such as expected return, and compares the subsequent performance of the groups. Researchers commonly set periodic breakpoints from the cross-sectional distribution of the chosen variable, then form…
The document asks how a portfolio can have negative or nearly flat realized returns during a period while reporting positive Fama–French three-factor alpha. It presents the familiar regression relationship between excess portfolio returns, market excess…