A Heteroskedasticity-Consistent Covariance Matrix Estimator and a Direct Test for Heteroskedasticity

By Halbert White. 1980

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

The Econometrics of Randomized Experiments (2016, methodology): “For the Lalonde data the estimate and Neyman standard error, which are up to a degrees- of-freedom adjustment equal to the White robust standard errors (White, 1980), are τ̂ = 1.794 (ŝe 0.671).”
Heterogeneous Treatment Effects in Digital Experimentation (2014, positive): “We can target each linear mean using the population least-squares projections ( At posterior mean DGP, which has ω = 1 /n and ω d = 1 /n d , this becomes the difference of OLS projections in treatment and control.”
Applied Linear Regression (2004, background): “…like a rather poor estimate—after all, it is based mostly on the single observation yi—theoretical work by Eicker (1963, 1967), Huber (1967), and White (1980), among others, have shown that replacing σ 2W−1 by a diagonal matrix with the êi2 on the diagonal produces a consistent estimate of…”
Targeting of Transfers in Developing Countries: Review of Lessons and Experience (2004, methodology): “Targeting of transfers in developing countries: review of lessons and experience/ David Coady, Margaret Grosh, John Hoddinott. p. cm. – (World Bank regional and sectoral studies) Includes bibliographical references and index.”
Dynamic asset allocation under mean-reverting returns, stochastic interest rates, and inflation uncertainty: Are popular recommendations consistent with rational behavior? (2004, methodology): “…set { Θ: (Θ − Θ̂)Ω−1(Θ − Θ̂)′ ≤ 28.87 } where 28.87 is the 95%-percentile of the chi-square distribution with 18 degrees of freedom, and the variancecovariance matrix, Ω, is obtained based on the White (1980) variance-covariance matrix estimator used in calculating standard errors in Table 1.”
The impact of recent financial shocks on the financing and investment policies of UK private firms (2013, background): “We addressed these issues by adjusting the standard errors that are robust to serial correlations (Arellano, 1987; White, 1980).”
The impact of voluntary corporate disclosures on the ex-ante cost of capital for Swiss firms (2002, unknown): “The results obtained from estimating regression equation (7) using simple OLS are provided in Table 6, Panels A and B. Testing for the presence of heteroscedasticity does not indicate any problems (White, 1980), and, using Cook’s distance, no influential data points have been detected.”
Asymptotic inference under heteroskedasticity of unknown form (2004, methodology): “The most commonly used heteroskedasticity-consistent covariance matrix estimator (HCCME) is that proposed by Halbert White in an inEuential Econometrica paper (White, 1980), who built upon Eicker (1963).”
Effects of Employment Protection on Worker and Job Flows: Evidence from the 1990 Italian Reform (2008, methodology): “Moreover, since the error term of the linear model is heteroskedastic, we compute the White (1980) heteroskedasticity-robust variance matrix.”
Average Idiosyncratic Volatility in G7 Countries (2004, result): “The Newey-West (1987) tstatistics with 4 lags are in parentheses; and we find essentially the same results using the White (1980)-consistent t-statistics.”
Time Pressure and Creativity in Organizations: A Longitudinal Field Study (2002, methodology): “To correct for this, all analyses used heteroscedasticity-consistent standard errors (White, 1980), further corrected for clustering of observations within respondents (Rogers, 1993).”