Confounding

 

In Epidemiology a confounder is:

 

A researcher can only control a study or analysis for confounders that are:

 

Example: Grey hair predicts heart disease if it is put into a multiple regression model because it is unequally distributed between people who do have heart disease (the elderly) and those who don't (the young). Grey hair confounds thinking about heart disease because it is not a cause of heart disease.

 

Strategies to reduce confounding are:

 

 

Copyright © 2000-2019 StatsDirect Limited, all rights reserved. Download a free trial here.