On Estimating Variance of Robust Estimators when the Errors are Asymmetric.
Abstract
We investigate the effects of asymmetry on estimates of variance of robust estimator in location and regression problems, showing the heavy skewness of errors can seriously bias the common variance estimates for location and intercept, a problem that can be corrected by jackknifing for location but is more intractable for the intercept in regression. The scale parameters in regression seem not to be as seriously subject to this bias if the sample size is large compared to the number parameters. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- Aug 01, 1978
- Accession Number
- ADA072598
Entities
People
- Raymond J. Carroll
Organizations
- University of North Carolina at Chapel Hill