get_opt_gamma: Obtain Optimized Sensitivity Parameters Using Multivariate...

In JiajingZ/CopSens: Copula-Based Sensitivity Analysis for Observational Causal Inference

Obtain Optimized Sensitivity Parameters Using Multivariate Calibration Criterion

Description

Obtain Optimized Sensitivity Parameters Using Multivariate Calibration Criterion

Usage

get_opt_gamma(
  mu_y_dt,
  mu_u_dt,
  cov_u_t,
  sigma_y_t,
  R2_constr = 1,
  normtype = "L2",
  idx = NULL,
  ...
)

Arguments

mu_y_dt	Scalar or vector that contains naive estimates of treatment effects ignoring confounding.
mu_u_dt	Matrix of difference in conditional confounder means, E(U \mid t1) - E(U \mid t2), with latent variables in columns.
cov_u_t	Covariance matrix of confounders conditional on treatments.
sigma_y_t	Scalar of the standard deviation of outcome conditional on treatments.
R2_constr	an optional scalar or vector specifying the upper limit constraint on R^2 . By default, R2_constr = 1.
normtype	character. Optional function m for the multivariate calibration criterion. By default, the L2 norm will be applied. "L1" - apply the L1 norm, sum(abs(x)). "L2" - apply the L2 norm, sqrt(sum(x^2)). "Inf" - apply the infinity norm, max(abs(x)).
idx	A zero-one vector with 1 in the i-th coordinate if the i-th outcome to be applied with the MCC calibration over, otherwise 0.
...	further arguments passed to solve

Value

Optimized sensitivity parameters.

JiajingZ/CopSens documentation built on May 2, 2023, 6:45 a.m.