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 considers whether to constrain the intercept to zero when estimating a security’s factor beta from a single-factor time-series regression. Asset-pricing theory implies a zero intercept for excess returns, while practical regressions may produce…
The document asks whether returns used to construct the size and value components of a Fama–French three-factor model should be converted to the home currency when the market-return data have already been converted. The example concerns a Danish investor…
The discussion examines whether low-volatility stocks outperform high-volatility stocks over long periods and whether the result depends on the sample window. It points to research across equities and other asset classes that reports weak or absent positive…
The document seeks introductory resources on systematic strategies in fixed income, with particular interest in corporate bonds, options, and foreign exchange. The replies point to a research paper on systematic credit investing that covers investment-grade…
The document raises two questions about using principal component analysis on index and sector returns as predictors of a single stock’s return. It asks whether the first component, or a set of leading components, should explain a minimum share of variance…
The document describes an attempt to estimate three-factor Fama–French regressions for annual stock portfolios sorted into ROIC quartiles. The proposed setup creates four portfolios per year and regresses each constituent company’s annual excess return on…
The document compares ways to summarize price-to-book ratios across a sector, emphasizing that the appropriate measure depends on the intended use. A simple average or median of company ratios describes a typical constituent but can be distorted by extreme…
The document explores whether CAPM remains valid when investor preferences follow Prospect Theory, with utility that is concave for gains and convex for losses. It contrasts this pattern with the concave utility and mean-variance assumptions often used to…
The document considers why a regression of an individual stock’s returns on the Fama–French three factors produces a lower R-squared than expected from the original factor-model paper. The questioner describes aligning monthly stock returns with monthly…
The document considers whether Beneish’s M-Score, developed using US company data, can be applied to UK firms reporting under IFRS. Its answer is that the model may still be usable, but financial statements should first be brought into a common accounting…
The document asks whether a multi-factor rolling beta can be estimated by regressing a hedge fund index’s returns on several asset-class return series, then repeating the regression over a moving window. It confirms this as the basic approach, while warning…
The document explains why the Fama–French three-factor model adds size and book-to-market factors to the market factor. The cited account says the factors were selected because historical returns for small firms and firms with high book-to-market ratios…
The document asks how to pair weekly share prices with earnings when calculating price-to-earnings ratios. The responses explain that the earnings measure depends on the purpose of the analysis and the data available. Trailing twelve-month earnings are…
The document considers whether monthly investment returns can be expanded into daily observations for factor regressions and portfolio weight analysis. Its main proposal is stochastic backfilling: model the lower frequency asset’s return distribution,…
The document asks how a linear multifactor model for asset returns under Arbitrage Pricing Theory can imply a pricing kernel, or stochastic discount factor, that is linear in the same factors. It defines asset factor loadings, factor returns, residuals, and…
The document asks why Alphalens raises a length mismatch while cleaning factor data and computing forward returns. Its example aligns factor observations and price data by common assets and dates, then removes the final price date, yet still encounters…
The document describes an attempt to test valuation, size, and momentum premia with Fama-MacBeth regressions. The proposed design estimates factor loadings in rolling 60-month time-series regressions for 50 portfolios, then runs monthly cross-sectional…
The document explains that rolling CAPM beta can be calculated either by regression or from rolling correlation multiplied by the ratio of the asset’s standard deviation to the market’s. It argues that the estimation horizon should reflect the investor’s…
The document introduces factor grouping as a way to condition stock signals on categories such as sector or industry. It describes two common transformations: subtracting a group’s average return from each stock’s return, or ranking stocks within their…
The document poses an estimation problem for a single-factor asset pricing model when the factor is not itself a return. It specifies time-series regressions of asset excess returns on the factor, with intercepts constrained by factor loadings, the factor…
The discussion considers why a multivariate regression of monthly returns on fundamental factors such as valuation, book value, and cash flow may have strongly autocorrelated residuals. Suggested responses include fitting an ARMA model to the returns first…
The document clarifies how to calculate returns for portfolios formed by sorting S&P 500 companies on market-to-book ratios. For a value-weighted return within each bucket, each constituent’s monthly return is multiplied by its market capitalization divided…
The document raises a model-selection question for estimating an asset or fund’s beta and risk exposures to one or more factors: whether to fit a regression on a short recent window or a longer historical record. A short window can better reflect current…
The document explains industry fixed effects in cross-sectional regressions used in asset pricing. The method adds industry-specific constant terms, often implemented as indicator variables, to the regression. These terms capture average return differences…