Bias and sensitivity plan
Assess selection and measurement errors
Consider participation and source-population selection separately from exposure measurement and confounding. Sensitivity analyses should probe plausible mechanisms, rather than only changing a significance threshold.
Flow diagram
Steps
Assess selection mechanisms
Consider case ascertainment, control sampling and nonparticipation.
Assess exposure measurement error
Consider recall, differential misclassification and observer effects.
Assess confounding and overmatching
Justify matching and adjustment decisions.
Specify bias analyses
Define plausible alternative sampling, definitions or error parameters.
Qualify study conclusions
Document limits and supporting evidence.
Bias and sensitivity plan
End flow
Tables and supporting information
Bias analysis scenarios
Prespecify justified alternatives.