Working Paper: NBER ID: w10447
Authors: Gopal K. Basak; Ravi Jagannathan; Tongshu Ma
Abstract: We develop a jackknife estimator for the conditional variance of a minimum-tracking- error-variance portfolio constructed using estimated covariances. We empirically evaluate the performance of our estimator using an optimal portfolio of 200 stocks that has the lowest tracking error with respect to the S&P500 benchmark when three years of daily return data are used for estimating covariances. We find that our jackknife estimator provides more precise estimates and suffers less from in-sample optimism when compared to conventional estimators.
Keywords: jackknife estimator; tracking error variance; optimal portfolios; covariance estimation
JEL Codes: G11; G12
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| insample estimates of the variance of efficient portfolios constructed using estimated inputs (C51) | true out-of-sample variance (C52) |
| jackknife estimator (C51) | more accurate estimate of out-of-sample variance (C51) |
| sample covariance matrix (C10) | significant insample optimism (C24) |
| three-factor model (C38) | does not adequately capture the correlation structure (C10) |