EUVIMEDEUVIMED entdecken
Open Access

Three‐phase generalized raking and multiple imputation estimators to address error‐prone data

Gustavo Amorim iD, Ran Tao iD, Sarah Lotspeich iD, Pamela A Shaw iD, Thomas Lumley, Rena C Patel iD, Bryan E Shepherd

Statistics in Medicine · 2024

DOI: 10.1002/sim.9967 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Statistics in Medicine, 2024. Verfasst von Gustavo Amorim und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biostatistics, Vanderbilt University Medical Center, Nashville, Tennessee, USA. Hauptthemen laut MEDLINE: Electronic Health Records, Data Accuracy. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIH HHS, NIAID NIH HHS, Patient-Centered Outcomes Research Institute.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Validation studies are often used to obtain more reliable information in settings with error‐prone data. Validated data on a subsample of subjects can be used together with error‐prone data on all subjects to improve estimation. In practice, more than one round of data validation may be required, and direct application of standard approaches for combining validation data into analyses may lead to inefficient estimators since the information available from intermediate validation steps is only partially considered or even completely ignored. In this paper, we present two novel extensions of multiple imputation and generalized raking estimators that make full use of all available data. We show through simulations that incorporating information from intermediate steps can lead to substantial gains in efficiency. This work is motivated by and illustrated in a study of contraceptive effectiveness among 83 671 women living with HIV, whose data were originally extracted from electronic medical records, of whom 4732 had their charts reviewed, and a subsequent 1210 also had a telephone interview to validate key study variables.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Electronic Health RecordsData AccuracyFemaleHumansHIV Infections

Stichwörter der Autor:innen

data auditsdesign-based estimatorelectronic medical recordsmeasurement errormultiple imputationthree-phase design

Autor:innen und Institutionen

  • Department of Biostatistics, Vanderbilt University Medical Center, Nashville, Tennessee, USA.
  • Vanderbilt Genetics Institute, Vanderbilt University Medical Center, Nashville, Tennessee, USA.
  • Department of Statistical Sciences, Wake Forest University, Winston-Salem, North Carolina, USA.
  • Biostatistcs Division, Kaiser Permanente Washington Health Research Institute, Seattle, Washington, USA.
  • Department of Statistics, University of Auckland, Auckland, New Zealand.
  • Department of Medicine, University of Washington, Seattle, Washington, USA.

ORCID-Profile: Gustavo Amorim, Ran Tao, Sarah Lotspeich, Pamela A Shaw, Rena C Patel

Förderung

  • NIH HHS
  • NIAID NIH HHS
  • Patient-Centered Outcomes Research Institute
  • National Institutes of Health

Zitieren

APA

Amorim, G., Tao, R., Lotspeich, S., Shaw, P. A., Lumley, T., Patel, R. C., & Shepherd, B. E. (2024). Three‐phase generalized raking and multiple imputation estimators to address error‐prone data. Statistics in Medicine. https://doi.org/10.1002/sim.9967

Vancouver

Amorim G, Tao R, Lotspeich S, Shaw PA, Lumley T, Patel RC, et al. Three‐phase generalized raking and multiple imputation estimators to address error‐prone data. Statistics in Medicine. 2024. doi:10.1002/sim.9967

BibTeX
@article{Amorim2024,
  author = {Amorim, Gustavo and Tao, Ran and Lotspeich, Sarah and Shaw, Pamela A and Lumley, Thomas and Patel, Rena C and Shepherd, Bryan E},
  title = {Three‐phase generalized raking and multiple imputation estimators to address error‐prone data},
  journal = {Statistics in Medicine},
  year = {2024},
  doi = {10.1002/sim.9967}
}
Kostenlos starten →