Bias

Introduction

>

Learning Objectives

>

Student Role

>

Design Questions

>

Data Analysis Questions

>

Discussion Questions

>

Print Module

Introduction

Bias is defined as a systematic error which results in an incorrect or invalid estimate of the measure of association. Elucidating methods for eliminating bias from observational studies has long been one of the central goals of the field of epidemiology. The following exercise will introduce several different types of bias and some important ways of avoiding it.

Faculty Highlight: Steven D. Stellman, PhD

Dr. Steven Stellman's research has included studies of tobacco-related cancers and environmental factors in breast cancer. More recently, he has applied geographic information systems (GIS) in the studies of physical and mental health of Vietnam veterans in relation to exposure to Agent Orange and military combat. Prior to this study, the relation between saccharin obtained through artificial sweeteners or diet beverages and bladder cancer in humans was a matter of public health and scientific controversy. Dr. Stellman says that "Saccharin has been on the burner of epidemiology for over 125 years." Animal studies demonstrated a statistically significant increase of bladder tumors in male rats, while tumor-promoting effects were observed in both in vitro and in vivo studies.

Yet, published epidemiological studies had been negative. Based on the results of the study presented to you in this exercise it was concluded that there was no evidence that the regulated artificial sweeteners on the market in the United States were related to cancer risk in humans. Today, artificial sweeteners are continued to be regulated by the U.S. Food and Drug Administration (FDA).

Read a transcript of an interview of Dr. Stellman discussing his study of the relationship between saccharin use and bladder cancer. [ Link to transcript ]

Read more about Dr. Stellman's work in the following articles.

Good luck and have fun!