A Simple, Positive Semi-Definite, Heteroskedasticity and Autocorrelation Consistent Covariance Matrix¶
Why this mattered¶
TBD
Abstract¶
This paper describes a simple method of calculating a heteroskedasticity and autocorrelation consistent covariance matrix that is positive semi-definite by construction. It also establishes consistency of the estimated covariance matrix under fairly general conditions.
Related¶
- enables → Returns to Buying Winners and Selling Losers: Implications for Stock Market Efficiency — Newey-West HAC covariance estimation enabled robust inference for autocorrelated stock-return strategies such as momentum portfolios.
- enables → How Much Should We Trust Differences-In-Differences Estimates? — Newey-West HAC covariance estimation addressed serial correlation in standard errors, a problem central to Bertrand, Duflo, and Mullainathan's critique of difference-in-differences inference.
- enables → Testing the null hypothesis of stationarity against the alternative of a unit root — Newey and West's HAC covariance estimator enabled KPSS to construct a robust Lagrange-multiplier stationarity test under serial correlation and heteroskedasticity.
- cite ← Returns to Buying Winners and Selling Losers: Implications for Stock Market Efficiency — The momentum paper cites Newey and West's HAC covariance estimator to support inference robust to heteroskedasticity and autocorrelation in return regressions.
- cite ← Testing for a unit root in time series regression — Phillips and Perron use Newey and West's HAC covariance idea to make unit-root test statistics robust to autocorrelation and heteroskedasticity.
- cite ← How Much Should We Trust Differences-In-Differences Estimates? — The differences-in-differences paper invokes Newey-West HAC covariance estimation as a baseline method for correcting serial correlation in standard errors.
- cite ← Testing the null hypothesis of stationarity against the alternative of a unit root — KPSS uses Newey and West's positive semi-definite HAC covariance estimator to handle serial correlation in the stationarity test statistic.
Sources¶
- DOI: https://doi.org/10.2307/1913610
- OpenAlex: https://openalex.org/W2117178635