Implements novel nonparametric approaches to address biases and confounding when comparing treatments or exposures in observational studies of outcomes. While designed and appropriate for use in studies involving medicine and the life sciences, the package can be used in other situations involving outcomes with multiple confounders. The package implements a family of methods for nonparametric bias correction when comparing treatments in cross-sectional, case-control, and survival analysis settings, including competing risks with censoring. The approach extends to bias-corrected personalized predictions of treatment outcome differences, and analysis of heterogeneity of treatment effect-sizes across patient subgroups.
LocalControl is an R package implementing novel nonparametric approaches to address biases and confounding when comparing treatments or exposures in observational studies of outcomes.
See R help pages for examples on how to run each of the package functions.
LocalControl is licensed under Apache License 2.0
Stable? (Let people know what their expectations should be)
Deprecated the localControlCompetingRisks(), localControlNearestNeighbors(), and (hidden) doLocalControl() functions.
Added a new function in their place, LocalControl().
The behavior of the three removed functions now exists in this function.
The new “outcomeType” parameter allows users to toggle between the competingRisks and NearestNeighbors functionality.
Deprecated the plotLocalControlCIF and plotLocalControlLTD functions, replaced with s3 (plot()) functions.
Added S3 functions: print() and summary() have also been added for the LocalControl classes.
Changed the structure of the LocalControlCS and LocalControlCR objects.
Removed the summary object.
The summary is now created upon request using the summary() s3 function with the LocalControl classes.
Added a formula interface for LocalControl (beta).
LocalControl(data = lindner, modelForm = formula('cardbill ~ abcix | stent + female + acutemi'))
Is now a valid alternative to:
LocalControl( data = lindner, clusterVars = c("stent", "female", "acutemi"), treatmentColName = "abcix", outcomeColName = "cardbill")