ConfoundedMeta (version 1.3.0)
Sensitivity Analyses for Unmeasured Confounding in Meta-Analyses
Description
Conducts sensitivity analyses for unmeasured confounding in
random-effects meta-analysis per Mathur & VanderWeele (in preparation).
Given output from a random-effects meta-analysis with a relative risk
outcome, computes point estimates and inference for: (1) the proportion
of studies with true causal effect sizes more extreme than a specified threshold
of scientific significance; and (2) the minimum bias factor and confounding
strength required to reduce to less than a specified threshold the proportion
of studies with true effect sizes of scientifically significant size.
Creates plots and tables for visualizing these metrics across a range of bias values.
Provides tools to easily scrape study-level data from a published forest plot or
summary table to obtain the needed estimates when these are not reported.