This website uses cookies to collect usage information in order to offer a better browsing experience. By browsing this site or by clicking on the "ACCEPT COOKIES" button you accept our Cookie Policy.

Estimating the Stock-Bond Correlation

The article “Estimating the Stock-Bond Correlation” first appeared on Alpha Architect Blog.

The Stock-Bond Correlation

  • Megan Czasonis, Mark Kritzman, and David Turkington
  • Journal of Portfolio Management
  • A version of this paper can be found here
  • Want to read our summaries of academic finance papers? Check out our Academic Research Insight category

What are the research questions?

The correlation between stock and bond returns is an integral component of hedging strategies, risk assessment, and minimization of risk in allocation decisions.  In the context of those strategies, the stock-bond correlation is typically estimated using monthly return data over a recent previous period.  This is a reasonable approach but has turned out to be an unreliable indicator for purposes of forming outlooks. The typical estimation assumes the correlation is unaffected by the interval of time that the return is calculated (i.e. weekly, monthly, annually, etc.).  Among others, this is an extreme assumption that does not stand up to scrutiny. The historical evidence is clear that the stock-bond correlation with respect to the time interval used to measure returns is unstable, and most likely due to patterns of autocorrelation across returns. We have previously covered challenges within stock and bond correlations here.

In this paper, the authors conduct an incremental analysis of three innovations for reliably forming an outlook about the long-term correlation of stocks and bonds.

The analysis proceeds as follows:

  • First, economic and financial market predictors are identified and added to a purely extrapolative model. The extrapolative model serves as a baseline measure and is comparable to conventional methods currently in use. Fundamental predictors include economic growth 1, inflation 2, the relative level of earnings yield 3, and volatility of stock and bond returns 4.
  • The second innovation adds a ‘pathway’ for economic and financial variables to contribute to the estimation. Paths are included as values for five previous periods of the independent variables.
  • Third, the partial sample regression, a relatively new approach to estimation, is used to form an outlook about the long-term stock-bond correlation. Partial sample regression essentially filters the historical returns for relevance, where relevance is defined as a statistical concept that emphasizes observations with statistical similarity (“Mahalanobis distances”) to current observations.  The reader is referred to the paper for more description.
  • Returns on the S&P 500 Index are used to represent equity returns and the Bloomberg US Long Treasury Index is used to represent bond returns.

What are the Academic Insights?

The correlation between the predictions from each model and the actual, subsequent single-period correlations of five-year returns are presented in Exhibit 3.  With respect to models 1 and 2, the most common extrapolative approaches, the performance was weakest and least reliable. Each exhibited a correlation of .23 with future stock-bond correlations.  When fundamental economic and financial variables are included the accuracy increases to .34 using the filtered regression.  If variability in the path of those variables is included, accuracy increases to .57.  In the best model, which uses the filtering function of the partial sample regression, the accuracy was .63.  A three-fold improvement over current approaches. What’s not to like?!

Why does it matter?

This was a short but informative piece on improving the estimation of long-term correlations. Not only are the results applicable to the stock-bond correlation, but they should apply to other asset classes as well. For other pair-wise combinations of asset classes, an empirical analysis is still necessary to establish usefulness, although the concepts explored in this piece do apply. A description of the estimation of this statistic may appear to be a relatively tedious subject to review, but it’s importance in application to hedging and asset allocation strategies is central to their success. As with most of Kritzman’s work, a summary or a full read of the article, is definitely worth your time.

Visit Alpha Architect Blog to learn about the most important chart from the paper.


  1. Economic Growth – measured as the annual percentage change in industrial production 
  2. Inflation – measured as the annual percentage change in the CPI 
  3. Relative Earnings Yield – measured by the natural log of S&P Index earnings yield/the 10-year Treasury rate 
  4. Volatility of Stock and Bond Returns – measured by the natural log of the 5-year trailing volatility of earning yield/the 5-year trailing volatility of the 10-year Treasury rate 

Past performance is not necessarily indicative of future results.

The results are hypothetical results and are NOT an indicator of future results and do NOT represent returns that any investor actually attained. Indexes are unmanaged, do not reflect management or trading fees, and one cannot invest directly in an index.

Disclosure: Alpha Architect

The views and opinions expressed herein are those of the author and do not necessarily reflect the views of Alpha Architect, its affiliates or its employees. Our full disclosures are available here. Definitions of common statistics used in our analysis are available here (towards the bottom).

This site provides NO information on our value ETFs or our momentum ETFs. Please refer to this site.

Disclosure: Interactive Brokers

Information posted on IBKR Traders’ Insight that is provided by third-parties and not by Interactive Brokers does NOT constitute a recommendation by Interactive Brokers that you should contract for the services of that third party. Third-party participants who contribute to IBKR Traders’ Insight are independent of Interactive Brokers and Interactive Brokers does not make any representations or warranties concerning the services offered, their past or future performance, or the accuracy of the information provided by the third party. Past performance is no guarantee of future results.

This material is from Alpha Architect and is being posted with permission from Alpha Architect. The views expressed in this material are solely those of the author and/or Alpha Architect and IBKR is not endorsing or recommending any investment or trading discussed in the material. This material is not and should not be construed as an offer to sell or the solicitation of an offer to buy any security. To the extent that this material discusses general market activity, industry or sector trends or other broad based economic or political conditions, it should not be construed as research or investment advice. To the extent that it includes references to specific securities, commodities, currencies, or other instruments, those references do not constitute a recommendation to buy, sell or hold such security. This material does not and is not intended to take into account the particular financial conditions, investment objectives or requirements of individual customers. Before acting on this material, you should consider whether it is suitable for your particular circumstances and, as necessary, seek professional advice.

trading top