Core concepts in pharmacoepidemiology: quantitative bias analysis
- Jeremy Brown,
- Jacob Hunnicutt N,
- Sanni Ali M,
- Krishnan Bhaskaran,
- Ashley Cole
, - Sinead Langan,
- Dorothea Nitsch,
- Christopher Rentsch
, - Nicholas Galwey,
- Kevin Wing,
- Ian Douglas
Sanni Ali M
London School of Hygiene & Tropical Medicine Department of Non-communicable Disease Epidemiology
Author ProfileKrishnan Bhaskaran
London School of Hygiene & Tropical Medicine Department of Non-communicable Disease Epidemiology
Author ProfileSinead Langan
London School of Hygiene & Tropical Medicine Department of Non-communicable Disease Epidemiology
Author ProfileDorothea Nitsch
London School of Hygiene & Tropical Medicine Department of Non-communicable Disease Epidemiology
Author ProfileChristopher Rentsch
![](https://d197for5662m48.cloudfront.net/assets/icons/omniauth/orcid-ca37582cd91a671ed5cec57770e0e96c01b4b79b8b5b75d8598fc1ddac18c974.svg)
London School of Hygiene & Tropical Medicine Department of Non-communicable Disease Epidemiology
Author ProfileKevin Wing
London School of Hygiene & Tropical Medicine Department of Non-communicable Disease Epidemiology
Author ProfileIan Douglas
London School of Hygiene & Tropical Medicine Department of Non-communicable Disease Epidemiology
Author ProfileAbstract
Pharmacoepidemiological studies provide important information on the
safety and effectiveness of medications, but the validity of study
findings can be threatened by residual bias. Ideally, biases would be
minimised through appropriate study design and statistical analysis
methods. However, residual biases can remain, for example due to
unmeasured confounders, measurement error, or selection into the study.
A group of sensitivity analysis methods, termed quantitative bias
analyses, are available to assess, quantitatively and transparently, the
robustness of study results to these residual biases. These approaches
include methods to quantify how the estimated effect would be altered
under specified assumptions about the potential bias, and methods to
calculate bounds on effect estimates. This article introduces
quantitative bias analyses for unmeasured confounding,
misclassification, and selection bias, with a focus on their relevance
and application to pharmacoepidemiological studies.