Factor Regression

• What drove returns? The beta table shows how strongly the portfolio moved with the factors in the selected model.
• Was performance just factor exposure? Alpha and residual diagnostics show how much return remains after the selected factors are accounted for.
• How believable is the fit? R-squared, F-statistic, and residual dispersion indicate whether the factor model explains most of the observed behavior.

• The regression uses excess returns: portfolio returns minus the Fama-French risk-free series.
• Factor availability matters because each model has a different history. Later-starting models can shorten the usable sample window, and the tool surfaces that adjustment.
• Monthly mode compounds daily observations and excludes incomplete first and last months. Annual mode compounds daily observations into calendar-year returns and drops incomplete edge years.
• The portfolio configuration reuses the same typed portfolio model as the backtester, but cashflows are excluded because they distort return attribution.

• The tool accepts exactly one portfolio. Use the same allocation editor as Portfolio Backtest, but keep the analysis focused on one finished portfolio rather than a comparison set.
• Cashflows are not supported in this analysis. If you need to evaluate a DCA or withdrawal plan, use Portfolio Backtest first and then run factor regression on the underlying static portfolio configuration.
• Custom factors can be defined in the advanced settings panel. Each custom factor is a long-short spread built from public ticker returns. Specify tickers and weights (which must sum to zero), and the custom factor return series will be added as an additional regressor alongside the selected factor model.
• After the run, you can save, share, and reopen the analysis from your workspace just like other major tools.

Start with annualized alpha, R-squared, and the market beta. The coefficient table now includes exact p-values and 95% confidence intervals for each factor loading, computed from the t-distribution. Use the F-statistic to evaluate whether the model as a whole is jointly significant. Then use the fitted-versus-actual chart and residual series to see whether the model errors are persistent, regime-specific, or mostly noise. The residual summary panel provides mean, standard deviation, skewness, and excess kurtosis of the regression residuals.

• P-values use the exact t-distribution with n - k - 1 degrees of freedom, where n is the number of observations and k is the number of factors. Significance markers: *** p < 0.001, ** p < 0.01, * p < 0.05.
• Confidence intervals are 95% two-tailed, computed from the same t-distribution critical values.
• F-statistic tests joint significance of all factor loadings (excluding the intercept). A large F with a small p-value means the factors collectively explain meaningful variation.
• Intercept diagnostics report standard error, t-stat, p-value, and confidence interval for the alpha estimate itself.
• Residual summary reports mean (should be near zero for OLS), standard deviation, min, max, skewness, and excess kurtosis. Heavy tails or skew may indicate the factor model is missing an important driver.

• CAPM is the simplest baseline when you only want market beta and alpha.
• Fama-French 3 Factor is a strong default for broad equity portfolios with size and value tilts.
• Carhart 4 Factor is useful when momentum may explain part of the return pattern.
• Fama-French 5 Factor adds profitability and investment exposures to the 3-factor model.
• q-Factor (Hou-Xue-Zhang) is an investment-based model with market, size, investment-to-assets, and return-on-equity factors. Monthly frequency is recommended as daily q-factor data is not publicly available.
• AQR Multi-Factor provides a comprehensive model with market, size, value, momentum, betting-against-beta, and quality factors. It is useful for portfolios that blend multiple style tilts.
• Fixed Income Factors provides term spread, default spread, and corporate bond excess return factors for fixed income attribution. Use this when the portfolio has significant bond exposure.

• CAPM and FF3 use data from July 1926 onward.
• Carhart 4 Factor momentum data is available from November 1926 onward.
• Fama-French 5 Factor daily data begins July 1963.
• q-Factor monthly data is available from January 1967 onward.
• AQR Multi-Factor coverage varies by factor; US equity factors are generally available from the early 1970s onward.
• Fixed Income Factors are typically available from the mid-1960s onward.
• When the requested date range extends beyond factor data coverage, the tool trims the regression window and surfaces a warning.

• Check Annualized Alpha last, not first. A tiny alpha with a very high R-squared often means the portfolio is mostly a repackaged factor bet.
• Read the beta table next. Large positive market beta means broad equity exposure. Negative SMB or HML betas mean the portfolio behaves more like large-cap or growth-heavy equity exposure, respectively.
• Check p-values and confidence intervals to assess whether each factor loading is statistically distinguishable from zero at the sample size.
• Use the residual chart to look for clusters. If misses are concentrated in one crisis or regime, the model is telling you that a missing driver matters.

1. Open Factor Regression.
2. Configure one portfolio using the allocation editor. Cashflows are not supported in this tool because they distort return attribution.
3. Select a factor model. CAPM gives market beta and alpha. Fama-French 3 adds size and value. Carhart 4 adds momentum. Fama-French 5 adds profitability and investment.
4. Run the regression and read the beta table to see how strongly the portfolio moved with each factor.
5. Check R-squared to see how much of the behavior the model explains. Use the residual chart to look for unexplained clusters in specific periods.