On Detecting Influential Data and Selecting Regression Variables

Abstract

We consider a linear regression model. We attempt to measure the influence on the residual for the full model and the reduced model. A criterion to select important independent regression variables is also derived using the influence diagnostics. This criterion turns out to be the same as the one proposed by Gupta and Huang (1988).

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 01, 1989
Accession Number
ADA216387

Entities

People

  • Deng Yuang Huang
  • Shanti Gupta

Organizations

  • Purdue University

Tags

DTIC Thesaurus Topics

  • Computations
  • Contracts
  • Data Analysis
  • Gasoline
  • Information Science
  • Measurement
  • Military Research
  • New York
  • Observation
  • Petroleum
  • Probability
  • Random Variables
  • Residuals
  • Statistical Samples
  • Statistics
  • Universities
  • Vapor Pressure

Fields of Study

  • Mathematics

Readers

  • Regression Analysis.