bound_propensity: Bound Generalized Propensity Score

In txshift: Efficient Estimation of the Causal Effects of Stochastic Interventions

Description

Bound Generalized Propensity Score

Usage

bound_propensity(vals)

Arguments

vals	numeric vector of propensity score estimate values. Note that, for this parameter, the propensity score is (conditional) density and so it ought not be bounded from above.

Details

Bound estimated values of the generalized propensity score (a conditional density) to avoid numerical instability issues arising from practical violations of the assumption of positivity.

Value

A numeric vector of the same length as vals, where the returned values are bounded such that the minimum is no lower than 1/n, for the sample size n.

txshift documentation built on Feb. 11, 2022, 1:08 a.m.