EUVIMEDEUVIMED entdecken
Open Access

Measurement error-robust causal inference via constructed instrumental variables

Caleb H Miles iD, Linda Valeri iD, Brent Coull iD

Biometrics · 09.04.2026 · 82 (2)

DOI: 10.1093/biomtc/ujag057 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biometrics, online erschienen am 17.04.2026. Verfasst von Caleb H Miles und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biostatistics, Columbia University, New York, NY 10032, United States. Hauptthemen laut MEDLINE: Causality, Models, Statistical. Die Arbeit nennt 21 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIA NIH HHS, NIEHS NIH HHS, NIH/NIEHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Measurement error can often be harmful when estimating causal effects. Two scenarios in which this is the case are in the estimation of (a) the average treatment effect when confounders are measured with error, and (b) the natural indirect effect when the exposure and/or confounders are measured with error. Methods adjusting for measurement error typically require external data or knowledge about the measurement error distribution. Here, we propose methodology not requiring any such information. Instead, we show that when the outcome regression is linear in the error-prone variables, consistent estimation of these causal effects can be recovered using constructed instrumental variables (IVs) under certain conditions. These variables, which are functions of only the observed data, behave like IVs for the error-prone variables. Using data from a study of the effects of prenatal exposure to heavy metals on growth and neurodevelopment in Bangladeshi mother–infant pairs, we apply our methodology to estimate (a) the effect of lead exposure on birth length while controlling for maternal protein intake, and (b) lead exposure’s role in mediating the effect of maternal protein intake on birth length. Protein intake is calculated from food journal entries, and is suspected to be highly prone to measurement error.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

CausalityModels, StatisticalHumansFemalePregnancyData Interpretation, StatisticalComputer SimulationLeadPrenatal Exposure Delayed EffectsBiometryMaternal Exposure

Stichwörter der Autor:innen

causal inferenceenvironmental healthinstrumental variablemeasurement errormediation analysisnutrition

Substanzen

Lead

Autor:innen und Institutionen

  • Department of Biostatistics, Columbia University, New York, NY 10032, United States.
  • Department of Biostatistics, Harvard University, Boston, MA 02115, United States.

ORCID-Profile: Caleb H Miles, Linda Valeri, Brent Coull

Förderung

  • NIA NIH HHS
  • NIEHS NIH HHS
  • NIH/NIEHS
  • NCATS NIH HHS

Zitieren

APA

Miles, C. H., Valeri, L., & Coull, B. (2026). Measurement error-robust causal inference via constructed instrumental variables. Biometrics, 82(2). https://doi.org/10.1093/biomtc/ujag057

Vancouver

Miles CH, Valeri L, Coull B. Measurement error-robust causal inference via constructed instrumental variables. Biometrics. 2026;82(2). doi:10.1093/biomtc/ujag057

BibTeX
@article{Miles2026,
  author = {Miles, Caleb H and Valeri, Linda and Coull, Brent},
  title = {Measurement error-robust causal inference via constructed instrumental variables},
  journal = {Biometrics},
  year = {2026},
  volume = {82},
  number = {2},
  doi = {10.1093/biomtc/ujag057}
}
Kostenlos starten →