scientific article; zbMATH DE number 3945137
From MaRDI portal
Publication:3716100
[For the entire collection see Zbl 0583.00027.] In this paper we introduce a new class of estimators, ridge type M- estimators, designed for analyzing linear regression models when regressor variables are multicollinear and residual distributions display long tails. The estimators are defined as weighted maximum likelihood type (M-) estimators when additional information about the parameters is given. An example shows that conclusions based on a ridge type M-estimator can be rather different from conclusions based on the M-estimator and from the ordinary ridge regression estimator.
Recommendations
Cited in
(6)- Restricted M-estimation
- Rank-based ridge estimation in multiple linear regression
- On some ridge regression estimators: a nonparametric approach
- scientific article; zbMATH DE number 3915447 (Why is no real title available?)
- scientific article; zbMATH DE number 1263749 (Why is no real title available?)
- Developing ridge estimation method for median regression
This page was built for publication:
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3716100)