Huber-White standard errors

From Wikipedia, the free encyclopedia

In econometrics, Huber-White standard errors are standard errors that are adjusted for correlations of error terms across observations, especially in panel and survey data as well as data with cluster structure. This type of adjusted errors is also called Sandwich, robust or empirical standard errors.

Once obtained, these estimated errors should be used instead of traditional standard error estimates for inferences and hypothesis testing of the econometric model.

[edit] References

• Huber, P. J. (1967). ""The behavior of maximum likelihood estimates under non-standard conditions"". Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability 4: 221-233.. 
• White, H. (1980). ""A Heteroskedasticity-Consistent Covariance Matrix Estimator and a Direct Test for Heteroskedasticity"". Econometrica 48: 817-838. 
• Nawar, Abdel-Hameed (2005) "Seemingly Unrelated Regressions (SUR): An Introduction by Examples," A Statistics Lecture Note, New York University, July, mimeo
• Greene, William. (1998). "Econometric Analysis". Prentice Hall.