Methods for the Selection of Covariates in Nutritional Epidemiology Studies: A Meta-Epidemiological Review.
confounding
covariate
model building
nutritional epidemiology
research methods
Journal
Current developments in nutrition
ISSN: 2475-2991
Titre abrégé: Curr Dev Nutr
Pays: United States
ID NLM: 101717957
Informations de publication
Date de publication:
Oct 2019
Oct 2019
Historique:
received:
20
08
2019
accepted:
05
09
2019
entrez:
11
10
2019
pubmed:
11
10
2019
medline:
11
10
2019
Statut:
epublish
Résumé
Observational studies provide important information about the effects of exposures that cannot be easily studied in clinical trials, such as nutritional exposures, but are subject to confounding. Investigators adjust for confounders by entering them as covariates in analytic models. The aim of this study was to evaluate the reporting and credibility of methods for selection of covariates in nutritional epidemiology studies. We sampled 150 nutritional epidemiology studies published in 2007/2008 and 2017/2018 from the top 5 high-impact nutrition and medical journals and extracted information on methods for selection of covariates. Most studies did not report selecting covariates a priori (94.0%) or criteria for selection of covariates (63.3%). There was general inconsistency in choice of covariates, even among studies investigating similar questions. One-third of studies did not acknowledge potential for residual confounding in their discussion. Studies often do not report methods for selection of covariates, follow available guidance for selection of covariates, nor discuss potential for residual confounding.
Sections du résumé
BACKGROUND
BACKGROUND
Observational studies provide important information about the effects of exposures that cannot be easily studied in clinical trials, such as nutritional exposures, but are subject to confounding. Investigators adjust for confounders by entering them as covariates in analytic models.
OBJECTIVE
OBJECTIVE
The aim of this study was to evaluate the reporting and credibility of methods for selection of covariates in nutritional epidemiology studies.
METHODS
METHODS
We sampled 150 nutritional epidemiology studies published in 2007/2008 and 2017/2018 from the top 5 high-impact nutrition and medical journals and extracted information on methods for selection of covariates.
RESULTS
RESULTS
Most studies did not report selecting covariates a priori (94.0%) or criteria for selection of covariates (63.3%). There was general inconsistency in choice of covariates, even among studies investigating similar questions. One-third of studies did not acknowledge potential for residual confounding in their discussion.
CONCLUSION
CONCLUSIONS
Studies often do not report methods for selection of covariates, follow available guidance for selection of covariates, nor discuss potential for residual confounding.
Identifiants
pubmed: 31598577
doi: 10.1093/cdn/nzz104
pii: nzz104
pmc: PMC6778415
doi:
Types de publication
Journal Article
Langues
eng
Pagination
nzz104Informations de copyright
Copyright © American Society for Nutrition 2019.
Références
BMJ Open. 2017 Dec 27;7(12):e014633
pubmed: 29284712
Adv Nutr. 2016 May 16;7(3):423-32
pubmed: 27184269
BMJ. 2004 Oct 16;329(7471):883
pubmed: 15469946
Am J Epidemiol. 2011 Dec 1;174(11):1213-22
pubmed: 22025356
Am J Epidemiol. 2008 Mar 1;167(5):523-9; discussion 530-1
pubmed: 18227100
Am J Epidemiol. 2006 Jun 15;163(12):1149-56
pubmed: 16624967
Ann Intern Med. 2019 Jan 15;170(2):108-111
pubmed: 30597486
J Clin Oncol. 1993 Nov;11(11):2072-80
pubmed: 8229121
Eur J Epidemiol. 2007;22(7):413-5
pubmed: 17484029
PLoS Med. 2007 Oct 16;4(10):e296
pubmed: 17941714
Pharmacoepidemiol Drug Saf. 2013 Nov;22(11):1139-45
pubmed: 24006330
Medicine (Baltimore). 2016 May;95(20):e3653
pubmed: 27196467
Biometrics. 1998 Sep;54(3):948-63
pubmed: 9750244
Epidemiology. 1999 Jan;10(1):37-48
pubmed: 9888278
BMC Public Health. 2017 Apr 20;17(1):343
pubmed: 28427426
Ann Epidemiol. 2008 Oct;18(10):746-51
pubmed: 18693038
Int J Obes (Lond). 2005 Oct;29(10):1153-67
pubmed: 15997250
Clin J Am Soc Nephrol. 2017 Mar 7;12(3):546-552
pubmed: 27553952
Biometrics. 2011 Dec;67(4):1406-13
pubmed: 21627630
Am J Epidemiol. 1993 Dec 1;138(11):923-36
pubmed: 8256780
Epidemiology. 2016 May;27(3):368-77
pubmed: 26841057
Int J Epidemiol. 2016 Apr;45(2):565-75
pubmed: 27097747
BMJ. 2016 Apr 27;352:i1981
pubmed: 27121591
Nutr Hosp. 2011 Jul-Aug;26(4):784-91
pubmed: 22470024
Annu Rev Public Health. 2015 Mar 18;36:89-108
pubmed: 25785886
PLoS One. 2014 Jan 17;9(1):e85355
pubmed: 24465543
Nutr J. 2018 Aug 11;17(1):75
pubmed: 30098591
Int J Obes (Lond). 2005 Jan;29(1):122-8
pubmed: 15545976
Am J Public Health. 2018 May;108(5):616-619
pubmed: 29565659
Epidemiology. 2003 May;14(3):300-6
pubmed: 12859030
J Epidemiol Community Health. 2014 Nov;68(11):1096-100
pubmed: 24923805
Ann Am Thorac Soc. 2019 Jan;16(1):22-28
pubmed: 30230362
Can J Surg. 2012 Apr;55(2):132-8
pubmed: 22564517
Eur J Epidemiol. 2009;24(12):733-6
pubmed: 19967429
J Clin Epidemiol. 2016 Jan;69:217-24
pubmed: 26327488
Ann Intern Med. 2002 Jan 15;136(2):122-6
pubmed: 11790063
JAMA. 2012 Aug 22;308(8):773-4
pubmed: 22910753
Am J Epidemiol. 1989 Jan;129(1):125-37
pubmed: 2910056
Am J Epidemiol. 2000 Mar 1;151(5):531-9
pubmed: 10707923
Int J Epidemiol. 1978 Dec;7(4):373-5
pubmed: 744677
J Clin Epidemiol. 2015 Sep;68(9):1046-58
pubmed: 26279400
J Am Diet Assoc. 2008 Jul;108(7):1134-44; discussion 1145
pubmed: 18589019
J Clin Epidemiol. 2018 Jan;93:94-102
pubmed: 28943377
Respirology. 2014 Apr;19(3):303-11
pubmed: 24447391
Stat Med. 2015 Oct 15;34(23):3133-43
pubmed: 26011599
Stat Methods Med Res. 2012 Feb;21(1):7-30
pubmed: 21075803