EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Interval estimate of causal effect in summary data based Mendelian randomization in the presence of winner's curse

Kai Wang iD

Genetic Epidemiology · 2024-03 · 48 (2) · 74-84

DOI: 10.1002/gepi.22545 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Genetic Epidemiology, online erschienen am 28.01.2024. Verfasst von Kai Wang. Beteiligte Einrichtung: Department of Biostatistics, College of Public Health, The University of Iowa, Iowa City, Iowa, USA. Hauptthemen laut MEDLINE: Mendelian Randomization Analysis, Models, Genetic. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This research focuses on the interval estimation of the causal effect of an exposure on an outcome using the summary data‐based Mendelian randomization (SMR) method while accounting for the winner's curse caused by the selection of single nucleotide polymorphism instruments. This issue is understudied and is important as the point estimate is biased. Since Fieller's theorem and its variations are not suitable for constructing a confidence interval, we use the box method. This box method is known to be conservative and thus provides a lower bound on the coverage level. To assess the performance of the box method, we use simulation studies and compare it with the support interval we proposed earlier and the Wald interval derived from the SMR method. All three methods are applied to a study of causal genes for Alzheimer's disease. Overall, the box method presents an alternative for constructing interval estimates for a causal effect while addressing the winner's curse issue.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Mendelian Randomization AnalysisModels, GeneticHumansComputer SimulationPolymorphism, Single NucleotideGenome-Wide Association Study

Stichwörter der Autor:innen

Alzheimer's diseaseFieller's theoremMendelian randomizationbox methodsummary statistics

Autor:innen und Institutionen

  • Department of Biostatistics, College of Public Health, The University of Iowa, Iowa City, Iowa, USA.

ORCID-Profile: Kai Wang

Zitieren

APA

Wang, K. (2024). Interval estimate of causal effect in summary data based Mendelian randomization in the presence of winner's curse. Genetic Epidemiology, 48(2), 74-84. https://doi.org/10.1002/gepi.22545

Vancouver

Wang K. Interval estimate of causal effect in summary data based Mendelian randomization in the presence of winner's curse. Genetic Epidemiology. 2024;48(2):74-84. doi:10.1002/gepi.22545

BibTeX
@article{Wang2024,
  author = {Wang, Kai},
  title = {Interval estimate of causal effect in summary data based Mendelian randomization in the presence of winner's curse},
  journal = {Genetic Epidemiology},
  year = {2024},
  volume = {48},
  number = {2},
  pages = {74--84},
  doi = {10.1002/gepi.22545}
}
Kostenlos starten →