# CVb: Critical values for CIs based on a biased Gaussian estimator. In kolesarm/RDHonest: Honest inference in sharp regression discontinuity designs

## Description

Computes the critical value cv_{1-alpha}(B) that is needed to make the confidence interval X\pm cv have coverage 1-alpha if X is Normally distributed with variance one and maximum bias at most B.

## Usage

 1 CVb(B, alpha = 0.05) 

## Arguments

 B Maximum bias, vector of non-negative numbers. alpha Determines CI level, 1-alpha. Needs to be between 0 and 1. Can be a vector of values.

## Value

Data frame with the following columns:

bias

Value of bias as specfied by bs

alpha

Value of α as specified by alpha

cv

Critical value

TeXDescription

LaTeX-friendly description of current row

## Examples

 1 2 3 # 90% critical value: CVb(B = 1, alpha = 0.1) CVb(B = c(0, 0.5, 1), alpha = c(0.05, 0.1)) 

kolesarm/RDHonest documentation built on April 3, 2018, 11:08 a.m.