cv: Critical values for inference based on a biased Gaussian...

In kolesarm/ATEHonest: Honest Inference for Treatment Effects under Unconfoundedness

Description

Critical value cv_{1-α}(B) such that the confidence interval X +- cv_{1-alpha}(B) will have coverage 1-α, where X is normally distributed with variance equal to 1 and bias bounded by B in absolute value.

Usage

cv(B, alpha = 0.05)

Arguments

B	Maximum bias, a non-negative vector.
alpha	Scalar between 0 and 1 determining the confidence level, 1-alpha

Value

Critical value cv_{1-alpha}(B)

Examples

# 90% critical value:
cv(B = 1, alpha = 0.1)
# 95% critical values
cv(B = c(0, 1, 3), alpha = 0.05)

kolesarm/ATEHonest documentation built on Nov. 14, 2020, 4:50 a.m.