get_kennedy_estimator: Kennedy Estimator

In JLDC/logib: Salary Analysis by the Swiss Federal Office for Gender Equality

Kennedy Estimator

Description

Computes the consistent and almost unbiased estimator for dummy variables in semi-logarithmic regressions proposed by Kennedy, P.E. (1981). Estimation with correctly interpreted dummy variables in semi-logarithmic equations. American Economic Review, 71, 801.

Usage

get_kennedy_estimator(coefficient, variance)

Arguments

coefficient	numeric value of the estimated coefficient for a dummy variable in a semi-logarithmic regression
variance	numeric value of the variance of this estimated coefficient

Details

Given a semi-logarithmic regression with a dummy variable and its estimated coefficient c with a variance v, the consistent and almost unbiased estimator proposed by Kennedy is computed as k = exp(c) / exp(v / 2) - 1

Value

a numeric value representing the so-called "Kennedy estimator"

JLDC/logib documentation built on Jan. 12, 2025, 4:13 p.m.