Rank-Based Inference without Symmetric Errors.
Abstract
Statistical inference based on ranks is reviewed. The role of a parameter and methods for its estimation are discussed. In particular, the use of density estimation methods is shown to provide a consistent estimate without the assumption of symmetry of the underlying distribution. The use of a consistent estimate in constructing hypothesis tests in the linear model without assuming symmetry is discussed.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jun 01, 1982
- Accession Number
- ADA116432
Entities
People
- James C. Aubuchon
- Thomas P. Hettmansperger
Organizations
- Pennsylvania State University