Information détaillée concernant le cours

[ Retour ]
Titre

The endogeneity problem in 'mediation' models

Dates

4th November 2024, 14:00-17:00

Organisateur(s)/trice(s)
Intervenant-e-s

Pr John Antonakis, UNIL

Description

The endogeneity problem in mediation models (3.0 hours)
A mediator is a dependent variable, m (e.g., charisma), that supposedly channels the effect of an independent variable, x (e.g., receiving training or not), on another dependent variable, y (e.g., subordinate performance). In experimental settings x is manipulated—subjects are randomized to treatment—to isolate the causal effect of x on downstream variables. If m is not or cannot be manipulated, which is usually the case, its causal effect on other variables cannot be determined and results cannot inform policy or practice. Unknown to many applied researchers is that popular mediation tests such as the Baron-Kenny or Preacher-Hayes approaches, as well as SEM analogs will yield incorrect parameter estimates. I will show why this problem occurs, and how instrumental-variable estimation recovers correct parameters.

 

Lieu

UNIL, Géopolis building, room 4799

Information
Places

20

Délai d'inscription 03.11.2024
short-url short URL

short-url URL onepage