Comparing single and multiple imputation strategies for harmonizing substance use data across HIV-related cohort studies.
Journal
BMC medical research methodology
ISSN: 1471-2288
Titre abrégé: BMC Med Res Methodol
Pays: England
ID NLM: 100968545
Informations de publication
Date de publication:
03 04 2022
03 04 2022
Historique:
received:
04
08
2021
accepted:
24
02
2022
entrez:
4
4
2022
pubmed:
5
4
2022
medline:
6
4
2022
Statut:
epublish
Résumé
Although standardized measures to assess substance use are available, most studies use variations of these measures making it challenging to harmonize data across studies. The aim of this study was to evaluate the performance of different strategies to impute missing substance use data that may result as part of data harmonization procedures. We used self-reported substance use data collected between August 2014 and June 2019 from 528 participants with 2,389 study visits in a cohort study of substance use and HIV. We selected a low (heroin), medium (methamphetamine), and high (cannabis) prevalence drug and set 10-50% of each substance to missing. The data amputation mimicked missingness that results from harmonization of disparate measures. We conducted Monte Carlo simulations to evaluate the comparative performance of single and multiple imputation (MI) methods using the relative mean bias, root mean square error (RMSE), and coverage probability of the 95% confidence interval for each imputed estimate. Without imputation (i.e., listwise deletion), estimates of substance use were biased, especially for low prevalence outcomes such as heroin. For instance, even when 10% of data were missing, the complete case analysis underestimated the prevalence of heroin by 33%. MI, even with as few as five imputations produced the least biased estimates, however, for a high prevalence outcome such as cannabis with low to moderate missingness, performance of single imputation strategies improved. For instance, in the case of cannabis, with 10% missingness, single imputation with regression performed just as well as multiple imputation resulting in minimal bias (relative mean bias of 0.06% and 0.07% respectively) and comparable performance (RMSE = 0.0102 for both and coverage of 95.8% and 96.2% respectively). Our results from imputation of missing substance use data resulting from data harmonization indicate that MI provided the best performance across a range of conditions. Additionally, single imputation for substance use data performed comparably under scenarios where the prevalence of the outcome was high and missingness was low. These findings provide a practical application for the evaluation of several imputation strategies and helps to address missing data problem when combining data from individual studies.
Sections du résumé
BACKGROUND
Although standardized measures to assess substance use are available, most studies use variations of these measures making it challenging to harmonize data across studies. The aim of this study was to evaluate the performance of different strategies to impute missing substance use data that may result as part of data harmonization procedures.
METHODS
We used self-reported substance use data collected between August 2014 and June 2019 from 528 participants with 2,389 study visits in a cohort study of substance use and HIV. We selected a low (heroin), medium (methamphetamine), and high (cannabis) prevalence drug and set 10-50% of each substance to missing. The data amputation mimicked missingness that results from harmonization of disparate measures. We conducted Monte Carlo simulations to evaluate the comparative performance of single and multiple imputation (MI) methods using the relative mean bias, root mean square error (RMSE), and coverage probability of the 95% confidence interval for each imputed estimate.
RESULTS
Without imputation (i.e., listwise deletion), estimates of substance use were biased, especially for low prevalence outcomes such as heroin. For instance, even when 10% of data were missing, the complete case analysis underestimated the prevalence of heroin by 33%. MI, even with as few as five imputations produced the least biased estimates, however, for a high prevalence outcome such as cannabis with low to moderate missingness, performance of single imputation strategies improved. For instance, in the case of cannabis, with 10% missingness, single imputation with regression performed just as well as multiple imputation resulting in minimal bias (relative mean bias of 0.06% and 0.07% respectively) and comparable performance (RMSE = 0.0102 for both and coverage of 95.8% and 96.2% respectively).
CONCLUSION
Our results from imputation of missing substance use data resulting from data harmonization indicate that MI provided the best performance across a range of conditions. Additionally, single imputation for substance use data performed comparably under scenarios where the prevalence of the outcome was high and missingness was low. These findings provide a practical application for the evaluation of several imputation strategies and helps to address missing data problem when combining data from individual studies.
Identifiants
pubmed: 35369872
doi: 10.1186/s12874-022-01554-4
pii: 10.1186/s12874-022-01554-4
pmc: PMC8978400
doi:
Types de publication
Journal Article
Research Support, N.I.H., Extramural
Langues
eng
Sous-ensembles de citation
IM
Pagination
90Subventions
Organisme : NIDA NIH HHS
ID : U01 DA036267
Pays : United States
Organisme : NIDA NIH HHS
ID : U24 DA044554
Pays : United States
Informations de copyright
© 2022. The Author(s).
Références
Am Stat. 2007 Feb;61(1):79-90
pubmed: 17401454
Psychol Bull. 1990 Nov;108(3):339-62
pubmed: 2270232
J Urban Health. 2019 Jun;96(3):429-441
pubmed: 30136249
Psychol Methods. 2001 Dec;6(4):330-51
pubmed: 11778676
Med Care. 2006 Aug;44(8 Suppl 2):S13-24
pubmed: 16849964
Int J Epidemiol. 2013 Apr;42(2):402-11
pubmed: 22345312
Drug Alcohol Depend. 2020 Feb 1;207:107770
pubmed: 31841750
JMIR Res Protoc. 2019 Jan 24;8(1):e10738
pubmed: 30679146
Int J Epidemiol. 2018 Apr 1;47(2):393-394i
pubmed: 29688497
Prev Sci. 2007 Sep;8(3):206-13
pubmed: 17549635
Stat Med. 1999 Nov 30;18(22):3123-35
pubmed: 10544311
Int J Epidemiol. 2010 Oct;39(5):1179-89
pubmed: 19948780
Int Stat Rev. 2010 Apr;78(1):40-64
pubmed: 21743766
Int J Epidemiol. 2007 Apr;36(2):294-301
pubmed: 17213214
Stat Med. 2004 Sep 30;23(18):2827-43
pubmed: 15344189
Am J Epidemiol. 2017 Jun 1;185(11):1148-1156
pubmed: 30052739
Am J Epidemiol. 1999 May 15;149(10):955-62
pubmed: 10342805
Int J Epidemiol. 2021 Mar 3;50(1):31-40
pubmed: 33682886
Addiction. 2002 Sep;97(9):1183-94
pubmed: 12199834
Stat Methods Med Res. 1999 Mar;8(1):3-15
pubmed: 10347857
Stat Med. 2005 Jul 30;24(14):2111-28
pubmed: 15889392
NIDA Res Monogr. 1991;109:75-100
pubmed: 1661376