Interpreting Extreme CAPM Betas in Portfolio Return Models

Summary

The document considers whether assets with extreme estimated betas should be excluded when using CAPM to predict expected returns and calculate residual, or idiosyncratic, returns. The proposed model estimates monthly total returns against a global equity benchmark over a historical sample, then uses those estimates to describe returns in the same period. The author asks what range of beta values is reasonable and whether outlier assets should be removed instead of discarding individual outlier months.

No response, beta thresholds, or empirical analysis is included, so the document does not establish a rule for identifying implausible estimates. It does flag a limitation of the proposed filtering: removing assets can compromise portfolio-level beta calculations. The concern also reflects that a simplified market model does not capture broader investor liabilities and exposures. These limitations make the question useful as a prompt about model specification and outlier handling, rather than as evidence for a particular beta cutoff.

Key ideas

• CAPM beta estimates can be sensitive to unusual observations in monthly return data.
• Excluding assets based on extreme beta values changes the composition of the portfolio being modeled.
• The document gives no defensible threshold for deciding which beta estimates are unreasonable.
• A single benchmark factor omits other investor exposures and liabilities.

Tags

# what is a reasonable beta in CAPM?


# what is a reasonable beta in CAPM?












I want to predict expected returns for assets using a CAPM, to calculate unexpected (unpredictable, idiosyncratic, non-systemic) returns in portfolios.

My CAPM estimated on monthly total gross returns obviously have some outliers. Instead of throwing out the outlier months, I think I need to ignore entire assets with outlier betas. What range of betas would one consider reasonable?

My model is nothing more complicated to use the 1999-2007 monthly returns relative to the MSCI World total gross returns, and predict for the same period.

(Btw, I know my suggestion makes the beta calculation for the entire portfolio invalid, but I think I can take that loss as I cannot price everything in the portfolio, let alone considering hedging against the investor's consumption stream, swings in human capital, earnings potential, pension claims etc. anyway.)

Shown in full with attribution under the source's licence. Licence: CC BY-SA 4.0 (Stack Exchange)

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.