Parametric Estimation and Sensitivity Analysis of Direct and Indirect Effects

We implement functions to estimate and perform sensitivity analysis to unobserved confounding of direct and indirect effects introduced in Lindmark, de Luna and Eriksson (2018) . The estimation and sensitivity analysis are parametric, based on probit and/or linear regression models. Sensitivity analysis is implemented for unobserved confounding of the exposure-mediator, mediator-outcome and exposure-outcome relationships.


sensmediation 0.2.0

  • Optimization function changed from optimx to maxLik
  • Analytic Hessians of the log-likelihoods have been implemented
  • Default optimization method changed from BFGS to Newton Raphson
  • Arguments allowed to be passed to the maximization function (method and control)
  • The sensmediation argument covariance has been deprecated
  • The sensmediation arguments out.full, med.full and all.interactions have been deprecated
  • New sensmediation arguments: and
  • Errors in the analytic gradients of the cases with probit model.expl and continuous model.resp as well as cases with probit model.resp and continuous model.expl have been fixed.

Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.


0.3.0 by Anita Lindmark, 3 years ago

Browse source code at

Authors: Anita Lindmark <[email protected]>

Documentation:   PDF Manual  

GPL-2 license

Imports maxLik, mvtnorm, stats

Suggests testthat

See at CRAN