Document Detail


One model, several results: the paradox of the Hosmer-Lemeshow goodness-of-fit test for the logistic regression model.
MedLine Citation:
PMID:  11055275     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
BACKGROUND: The Hosmer-Lemeshow test, used extensively to assess the fit of the logistic regression model, is performed by several statistical packages. Recent studies have shown some problems in the use of this test when ties are present. These problems were attributed merely to the test implementation. METHODS: We analysed the order of the observations as an alternative explanation of the problem of ties. Using a data-set of 1393 intensive care unit (ICU) patients we performed the Hosmer-Lemeshow test with all possible subjects dispositions. RESULTS: We obtained about one million different P values, ranging from 0.01 to 0.95. DISCUSSION: It is already known that when the Hosmer-Lemeshow goodness-of-fit test is performed with a number of covariate patterns lower than the number of subjects, its result may be inaccurate. We showed that the extent of this problem could be relevant under particular conditions. We also suggest a strategy for estimating the extent of the problem and subsequent interpretation.
Authors:
G Bertolini; R D'Amico; D Nardi; A Tinazzi; G Apolone
Related Documents :
10399205 - Testing proportionality in the proportional odds model fitted with gee.
15387245 - Bayesian support vector regression using a unified loss function.
16850435 - A weighted logistic regression model for estimation of recurrence of adenomas.
25461335 - Sequential monte carlo tracking of the marginal artery by multiple cue fusion and rando...
9178985 - Malar recontouring using 3d bio-modelling.
20085815 - Improved kymography tools and its applications to mitosis.
Publication Detail:
Type:  Journal Article    
Journal Detail:
Title:  Journal of epidemiology and biostatistics     Volume:  5     ISSN:  1359-5229     ISO Abbreviation:  J Epidemiol Biostat     Publication Date:  2000  
Date Detail:
Created Date:  2001-03-09     Completed Date:  2001-05-31     Revised Date:  2007-11-15    
Medline Journal Info:
Nlm Unique ID:  9611181     Medline TA:  J Epidemiol Biostat     Country:  ENGLAND    
Other Details:
Languages:  eng     Pagination:  251-3     Citation Subset:  IM    
Affiliation:
Clinical Epidemiology Unit, Institute of Research Pharmacology Mario Negri, Ranica, Bergamo, Italy.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Hospital Mortality
Humans
Intensive Care Units
Italy
Logistic Models*
Predictive Value of Tests
Severity of Illness Index
Statistics as Topic / methods

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Historical HIV prevalence in Edinburgh Prison: a database-linkage study.
Next Document:  A comparison of primary and proxy respondent reports of habitual physical activity, using kappa stat...