update_nu: Update nu via augmented covariate adjustment

In PLUCR: Policy Learning Under Constraint

Update nu via augmented covariate adjustment

Description

Computes updated Nu predictions by adding the bias correction for all previous solutions at X using sigma_beta scaled by coefficients epsilon2_collection, then transforms back via the logistic function.

Usage

update_nu(
  A,
  X,
  nu0,
  epsilon2,
  theta_collection,
  prop_score,
  beta = 0.05,
  centered = FALSE
)

Arguments

A	A binary vector or matrix of length n indicating treatment assignment (0 or 1).
X	A matrix of covariates of size n x d (input data in ⁠[0,1]⁠).
nu0	A fold-specific function predicting adverse event outcome (Xi) given treatment (A) and covariates (X).
epsilon2	A numeric vector of GLM coefficients for each column in sigma_psi_collection.
theta_collection	A list of the optimal theta enabling the reconstruction of optimal sigma_beta applied to psi functions.
prop_score	A function that estimates the propensity score given treatment (A) and covariates (X).
beta	A non-negative numeric scalar controlling the sharpness of the probability function (0.05 by default).
centered	A logical value indicating whether to apply centering in sigma_beta (FALSE by default).

Value

A numeric vector of updated nu on the ⁠[0,1]⁠ scale.

PLUCR documentation built on March 30, 2026, 5:08 p.m.