THE ABUSE OF STEPWISE REGRESSION OR: EXPERIMENTS IN FISHING,

Abstract

The paper briefly discusses the inappropriate evaluation of stepwise regression results. The author employs a simple argument revealing the misleading significance levels that are customarily reported when using a stepwise regression program. Using such a program and applying standard statistical tests, experience has indicated that random numbers can produce, in the majority of cases, significant correlations at the 0.05 level. Until the development of better test statistics, a more prudent use of stepwise regression is suggested. (Author)

Document Details

Document Type
Technical Report
Publication Date
Feb 01, 1970
Accession Number
AD0701804

Entities

People

  • E. B. Brandt

Organizations

  • RAND Corporation

Tags

DTIC Thesaurus Topics

  • Computing-Related Activities
  • Data Science
  • Information Science
  • Interdisciplinary Science
  • Mathematical Analysis
  • Mathematics
  • Standards
  • Statistical Analysis
  • Statistical Tests
  • Statistics

Readers

  • Naval Personnel Management
  • Systems Analysis and Design