Historical Covariance Estimates for Portfolio Risk
Summary
The document distinguishes estimating a portfolio’s variance from using a covariance matrix in mean-variance optimization. A covariance matrix estimated from historical returns can be rank deficient when the number of observations is too small relative to the number of assets. That can prevent inversion for optimization, but calculating the variance of a specified portfolio does not itself require matrix inversion.
The answer cautions that having enough observations to calculate portfolio variance does not make the estimates reliable: individual variances and pairwise correlations may still be unstable. It names shrinkage estimation as a way to produce more stable covariance estimates in limited-data settings. The discussion is conceptual and does not compare estimators or provide empirical results, so it offers no specific recommendation about the appropriate sample length or shrinkage method for a given portfolio.
Key ideas
- Portfolio variance for specified holdings does not require inverting the covariance matrix.
- A historical covariance estimate may be rank deficient when observations are too few relative to assets.
- Unstable variance and correlation estimates can remain a concern even when matrix inversion is unnecessary.
- Shrinkage estimation is mentioned as a way to improve covariance stability.
Tags
Full text
# Computing covariance matrix with historical data # Computing covariance matrix with historical data I have been reading Active Portfolio Management by Grinold and Khan. In the chapter about risk, they mention, "The third elementary model relies on historical variances and covariances. This procedure is neither robust nor reasonable. Historical models rely on data from T periods to estimate the $NxN$ covariance matrix. If T is less than or equal to N, we can find active positions that will appear riskless! So the historical approach requires $T > N$. For a monthly historical covariance matrix of S&P 500 stocks, this would require more than 40 years of data." When forming mean-variance optimal portfolio, we would need to invert the covariance matrix hence, we require a full rank covariance matrix. In this case using historical returns is not robust. However, if the main intention is to compute an estimate of the variance of the portfolio $w'\Sigma w$ where $w$ is the weight or holdings of stock, in such a use case, we can estimate $\Sigma$ with $T<N$ right? As we are not inverting the covariance matrix, the concern of not full rank is less of an issue, right? Any help is very much appreciated! ## Answer by Dhruv Mahajan (score 1, accepted) https://quant.stackexchange.com/a/53929 I don’t see how just calculation of Portfolio variance would need an invertible var-covar matrix, I mean you don’t even have to use the matrix notation to calculate it. It may be so that lower time frames would output unstable values of the individual variances and pairwise correlations. However there are certain methods to achieve a stable covariance matrix in such cases like shrinkage estimation. You’d always be better off using such methods, the above paragraph just comments on the theoretical possibility of such a matrix.
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.