gms | German Medical Science

Kongress Medizin und Gesellschaft 2007

17. bis 21.09.2007, Augsburg

A few random thoughts about systematic error bias analysis, and reasons for it, in observational epidemiologic research

Meeting Abstract

Search Medline for

  • Timothy L. Lash - Boston University School of Public Health, Boston, Massachusetts, USA

Kongress Medizin und Gesellschaft 2007. Augsburg, 17.-21.09.2007. Düsseldorf: German Medical Science GMS Publishing House; 2007. Doc07gmds233

The electronic version of this article is the complete one and can be found online at: http://www.egms.de/en/meetings/gmds2007/07gmds233.shtml

Published: September 6, 2007

© 2007 Lash.
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by-nc-nd/3.0/deed.en). You are free: to Share – to copy, distribute and transmit the work, provided the original author and source are credited.


Outline

Text

Epidemiologic research is an exercise in measurement, so is inherently susceptible to non-random error or bias. Conventionally, epidemiologists quantify uncertainty arising only from random error, and address uncertainty from systematic error only qualitatively by way of a discussion of study limitations. This talk will illustrate the potential for errors in inference that arise from this conventional paradigm, some of which are rooted in cognitive psychology. These errors tend to favor causal conclusions over bias explanations for an observed association. The talk will also address alternatives to the conventional paradigm that quantify bias and uncertainty from systematic error, so should reduce the natural tendency toward favoring causal conclusions.