A Monte Carlo Study of Two Robust Alternatives of Least Square Regression Estimation
We give some Monte Carlo results on the performance of two robust alternatives to least squares regression estimation - least absolute residuals and the one-step "sine" estimator. We show how to scale the residuals for the sine estimator to achieve constant efficiency at the Gaussian across various choices of X-matrix and give some results for the contaminated Gaussian distribution.
-
-
Copy CitationRichard W. Hill and Paul W. Holland, "A Monte Carlo Study of Two Robust Alternatives of Least Square Regression Estimation," NBER Working Paper 0058 (1974), https://doi.org/10.3386/w0058.Download Citation
Published Versions
Hill, Richard W. and Paul W. Holland. "Two Robust Alternatives To Least-Squared Regression," Journal of the American Statistical Association, 1977, v72(360), 828-833.
More from the NBER
In addition to working papers, the NBER disseminates affiliates’ latest findings through a range of free periodicals—the NBER Reporter, the NBER Digest, the Bulletin on Health, the Bulletin on the Economics of Alzheimer's, and the Bulletin on Entrepreneurship—as well as research spotlights, lectures, and panel videos.
