Inference procedures for the L1 regression

It is well known that the L 1 estimators of the parameters of the regression model asymptotically follow a normal distribution. In this paper, using Monte Carlo approach, we determine the sample size at which we can use the normal distribution approximation to construct confidence intervals and test...

Full description

Saved in:
Bibliographic Details
Published in:Computational statistics & data analysis 1991-08, Vol.12 (1), p.79-85
Main Authors: Stangenhaus, Gabriela, Narula, Subhash C.
Format: Article
Language:English
Subjects:
convergence
coverage probability
Exact sciences and technology
Least absolute error
Linear inference, regression
Mathematics
Minimum sum of absolute errors
Monte Carlo experiment
Probability and statistics
Sciences and techniques of general use
Statistics
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:It is well known that the L 1 estimators of the parameters of the regression model asymptotically follow a normal distribution. In this paper, using Monte Carlo approach, we determine the sample size at which we can use the normal distribution approximation to construct confidence intervals and tests of hypothesis on the parameters in the L 1 regression model.
ISSN:0167-9473
1872-7352
DOI:10.1016/0167-9473(91)90104-A