Leverage and breakdown in L sub 1 regression. From: Journal of the American Statistical Association | Date: March 1, 1992| Author: Ellis, Steven P.; Morgenthaler, Stephan | COPYRIGHT 1992 American Statistical Association. This material is published under license from the publisher through the Gale Group, Farmington Hills, Michigan.  All inquiries regarding rights should be directed to the Gale Group.Copyright information

In this article the notion of leverage of a design point when fitting a linear regression model is interpreted geometrically. In the case of least squares fitting, the leverage indicators based on the diagonal of the hat matrix are widely applied. By interpreting these hat matrix indicators geometrically, leverage can be generalized to groups of design points, as well as to other methods of fitting. The article introduces a leverage indicator that is appropriate for [L.sub.1] regre...

Related newspaper, magazine, and journal articles from HighBeam Research

	The Pitman closeness of a class of scaled estimators. The American Statistician ; 1. INTRODUCTION For a parameter [Theta] with unbiased estimator [Mathematical Expression Omitted] Searls and Intarapanich (1990) proposed the scaled estimator [Mathematical Expression Omitted] to decrease the mean square error (MSE) of estimation. They observed that the MSE of [Mathematical
	Using process control charts to reduce production times. Plastics Engineering ; In a PVC powder plant where |Mathematical Expression Omitted~ and R charts were used to control and reduce manufacturing times, output was increased by 25% and the loss rate was lowered by 90%. Industrial engineers and production personnel are generally familiar with the use of |Mathematical
	A nonparametric test for independence between two vectors. Journal of the American Statistical Association ; 1. INTRODUCTION Consider the problem of detecting dependence between two random vectors, where the dimensions of the vectors may be different. The proposed test is based on a sample of pairs. Let {[Mathematical Expression Omitted], i = 1, . . ., n} denote a random sample of n pairs, with
	Elongational, hysteresis, and oscillatory flows of complex fluids. Polymer Engineering and Science ; INTRODUCTION In a previous publication (1), we presented a model to describe the rheological properties of complex structured fluids. The rheological properties depend on n, the current number of structural elements. When the fluid is deformed, the structure changes and the rate of change of n is
	Monte Carlo approximation of bootstrap variances. The American Statistician ; 1. INTRODUCTION A conscientious scientist returns from lunch excited about a statistical analysis of some new data carried out that morning revealing a scientifically important result. The scientist decides to double check the analysis which uses a state-of-the-art bootstrap method, but is

See all results.