One model, several results: the paradox of the Hosmer-Lemeshow goodness-of-fit test for the logistic regression model
- PMID: 11055275
One model, several results: the paradox of the Hosmer-Lemeshow goodness-of-fit test for the logistic regression model
Abstract
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.
Similar articles
-
Assessing the calibration of mortality benchmarks in critical care: The Hosmer-Lemeshow test revisited.Crit Care Med. 2007 Sep;35(9):2052-6. doi: 10.1097/01.CCM.0000275267.64078.B0. Crit Care Med. 2007. PMID: 17568333
-
Global goodness-of-fit tests in logistic regression with sparse data.Stat Med. 2002 Dec 30;21(24):3789-801. doi: 10.1002/sim.1421. Stat Med. 2002. PMID: 12483767
-
Veterans Affairs intensive care unit risk adjustment model: validation, updating, recalibration.Crit Care Med. 2008 Apr;36(4):1031-42. doi: 10.1097/CCM.0b013e318169f290. Crit Care Med. 2008. PMID: 18379226
-
Assessing contemporary intensive care unit outcome: an updated Mortality Probability Admission Model (MPM0-III).Crit Care Med. 2007 Mar;35(3):827-35. doi: 10.1097/01.CCM.0000257337.63529.9F. Crit Care Med. 2007. PMID: 17255863
-
A comparison of goodness-of-fit tests for the logistic regression model.Stat Med. 1997 May 15;16(9):965-80. doi: 10.1002/(sici)1097-0258(19970515)16:9<965::aid-sim509>3.0.co;2-o. Stat Med. 1997. PMID: 9160492 Review.
Cited by
-
Support Network Factors Associated With Naming a Health Care Decision-Maker and Talking About Advance Care Planning Among People Living With HIV.J Pain Symptom Manage. 2019 Dec;58(6):1040-1047. doi: 10.1016/j.jpainsymman.2019.08.019. Epub 2019 Aug 22. J Pain Symptom Manage. 2019. PMID: 31446009 Free PMC article.
-
Performance of SAPS II and SAPS 3 in intermediate care.PLoS One. 2013 Oct 9;8(10):e77229. doi: 10.1371/journal.pone.0077229. eCollection 2013. PLoS One. 2013. PMID: 24130860 Free PMC article.
-
The Modified A-DIVA Scale as a Predictive Tool for Prospective Identification of Adult Patients at Risk of a Difficult Intravenous Access: A Multicenter Validation Study.J Clin Med. 2019 Jan 26;8(2):144. doi: 10.3390/jcm8020144. J Clin Med. 2019. PMID: 30691137 Free PMC article.
-
Assessment of androgen receptor expression in breast cancer patients using 18 F-FDG PET/CT radiomics and clinicopathological characteristics.BMC Med Imaging. 2023 Jul 17;23(1):93. doi: 10.1186/s12880-023-01052-z. BMC Med Imaging. 2023. PMID: 37460990 Free PMC article.
-
Patterns and determinants of prescribed drug use among pregnant women in Adigrat general hospital, northern Ethiopia: a cross-sectional study.BMC Pregnancy Childbirth. 2020 Oct 15;20(1):624. doi: 10.1186/s12884-020-03327-7. BMC Pregnancy Childbirth. 2020. PMID: 33059613 Free PMC article.