A review of two journals found that articles using multivariable logistic regression frequently did not report commonly recommended assumptions

Kenneth Ottenbacher, Heather R. Ottenbacher, Leigh Tooth, Glenn V. Ostir

Research output: Contribution to journalArticle

76 Citations (Scopus)

Abstract

To examine if commonly recommended assumptions for multivariable logistic regression are addressed in two major epidemiological journals. Ninety-nine articles from the Journal of Clinical Epidemiology and the American Journal of Epidemiology were surveyed for 10 criteria: six dealing with computation and four with reporting multivariable logistic regression results. Three of the 10 criteria were addressed in 50% or more of the articles. Statistical significance testing or confidence intervals were reported in all articles. Methods for selecting independent variables were described in 82%, and specific procedures used to generate the models were discussed in 65%. Fewer than 50% of the articles indicated if interactions were tested or met the recommended events per independent variable ratio of 10:1. Fewer than 20% of the articles described conformity to a linear gradient, examined collinearity, reported information on validation procedures, goodness-of-fit, discrimination statistics, or provided complete information on variable coding. There was no significant difference (P >. 05) in the proportion of articles meeting the criteria across the two journals. Articles reviewed frequently did not report commonly recommended assumptions for using multivariable logistic regression.

Original languageEnglish (US)
Pages (from-to)1147-1152
Number of pages6
JournalJournal of Clinical Epidemiology
Volume57
Issue number11
DOIs
StatePublished - Nov 2004

Fingerprint

Logistic Models
Epidemiology
Confidence Intervals

Keywords

  • Outcomes research
  • Research design
  • Statistical tests

ASJC Scopus subject areas

  • Medicine(all)
  • Public Health, Environmental and Occupational Health
  • Epidemiology

Cite this

A review of two journals found that articles using multivariable logistic regression frequently did not report commonly recommended assumptions. / Ottenbacher, Kenneth; Ottenbacher, Heather R.; Tooth, Leigh; Ostir, Glenn V.

In: Journal of Clinical Epidemiology, Vol. 57, No. 11, 11.2004, p. 1147-1152.

Research output: Contribution to journalArticle

@article{6e4fe68268a94193969ba54210235792,
title = "A review of two journals found that articles using multivariable logistic regression frequently did not report commonly recommended assumptions",
abstract = "To examine if commonly recommended assumptions for multivariable logistic regression are addressed in two major epidemiological journals. Ninety-nine articles from the Journal of Clinical Epidemiology and the American Journal of Epidemiology were surveyed for 10 criteria: six dealing with computation and four with reporting multivariable logistic regression results. Three of the 10 criteria were addressed in 50{\%} or more of the articles. Statistical significance testing or confidence intervals were reported in all articles. Methods for selecting independent variables were described in 82{\%}, and specific procedures used to generate the models were discussed in 65{\%}. Fewer than 50{\%} of the articles indicated if interactions were tested or met the recommended events per independent variable ratio of 10:1. Fewer than 20{\%} of the articles described conformity to a linear gradient, examined collinearity, reported information on validation procedures, goodness-of-fit, discrimination statistics, or provided complete information on variable coding. There was no significant difference (P >. 05) in the proportion of articles meeting the criteria across the two journals. Articles reviewed frequently did not report commonly recommended assumptions for using multivariable logistic regression.",
keywords = "Outcomes research, Research design, Statistical tests",
author = "Kenneth Ottenbacher and Ottenbacher, {Heather R.} and Leigh Tooth and Ostir, {Glenn V.}",
year = "2004",
month = "11",
doi = "10.1016/j.jclinepi.2003.05.003",
language = "English (US)",
volume = "57",
pages = "1147--1152",
journal = "Journal of Clinical Epidemiology",
issn = "0895-4356",
publisher = "Elsevier USA",
number = "11",

}

TY - JOUR

T1 - A review of two journals found that articles using multivariable logistic regression frequently did not report commonly recommended assumptions

AU - Ottenbacher, Kenneth

AU - Ottenbacher, Heather R.

AU - Tooth, Leigh

AU - Ostir, Glenn V.

PY - 2004/11

Y1 - 2004/11

N2 - To examine if commonly recommended assumptions for multivariable logistic regression are addressed in two major epidemiological journals. Ninety-nine articles from the Journal of Clinical Epidemiology and the American Journal of Epidemiology were surveyed for 10 criteria: six dealing with computation and four with reporting multivariable logistic regression results. Three of the 10 criteria were addressed in 50% or more of the articles. Statistical significance testing or confidence intervals were reported in all articles. Methods for selecting independent variables were described in 82%, and specific procedures used to generate the models were discussed in 65%. Fewer than 50% of the articles indicated if interactions were tested or met the recommended events per independent variable ratio of 10:1. Fewer than 20% of the articles described conformity to a linear gradient, examined collinearity, reported information on validation procedures, goodness-of-fit, discrimination statistics, or provided complete information on variable coding. There was no significant difference (P >. 05) in the proportion of articles meeting the criteria across the two journals. Articles reviewed frequently did not report commonly recommended assumptions for using multivariable logistic regression.

AB - To examine if commonly recommended assumptions for multivariable logistic regression are addressed in two major epidemiological journals. Ninety-nine articles from the Journal of Clinical Epidemiology and the American Journal of Epidemiology were surveyed for 10 criteria: six dealing with computation and four with reporting multivariable logistic regression results. Three of the 10 criteria were addressed in 50% or more of the articles. Statistical significance testing or confidence intervals were reported in all articles. Methods for selecting independent variables were described in 82%, and specific procedures used to generate the models were discussed in 65%. Fewer than 50% of the articles indicated if interactions were tested or met the recommended events per independent variable ratio of 10:1. Fewer than 20% of the articles described conformity to a linear gradient, examined collinearity, reported information on validation procedures, goodness-of-fit, discrimination statistics, or provided complete information on variable coding. There was no significant difference (P >. 05) in the proportion of articles meeting the criteria across the two journals. Articles reviewed frequently did not report commonly recommended assumptions for using multivariable logistic regression.

KW - Outcomes research

KW - Research design

KW - Statistical tests

UR - http://www.scopus.com/inward/record.url?scp=9644302447&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=9644302447&partnerID=8YFLogxK

U2 - 10.1016/j.jclinepi.2003.05.003

DO - 10.1016/j.jclinepi.2003.05.003

M3 - Article

VL - 57

SP - 1147

EP - 1152

JO - Journal of Clinical Epidemiology

JF - Journal of Clinical Epidemiology

SN - 0895-4356

IS - 11

ER -