What is bias and confounding and why are they important?

Robert Larson, DVM, PhD, DACT, DACVPM (Epidemiology), DACAN

Professor, Production Medicine; Edgar E. and M. Elizabeth Coleman Chair Food Animal Production Medicine; Executive Director, Veterinary Medical Continuing Education; College of Veterinary Medicine, Kansas State University

Proceedings Paper (PDF) Slides (PDF) Screencast (video)
 
Download proceedings paper (PDF) Download slide deck (PDF) Stream presentation video
 

Please note: Some proceedings papers or presentation slide decks were not made available by the speaker. Also, selected screencast recordings from the webinar may be viewed only by active EBVMA members after logging into their member portal.

Abstract

Well-designed studies differ from clinical experience because explicit constraints are implemented to control for sources of bias. Clinical experience is particularly prone to bias because the same person provides and then evaluates interventions. Biases that occur commonly, and often inadvertently, when relying on clinical experience are typically grouped into categories of selection bias, information bias, and confounding.

Observations in clinical settings are plagued by selection bias because although this bias is a crucial flaw if one wants to compare interventions, it is perfectly appropriate and beneficial when applied to clinical case management. Essentially, selection bias occurs when animals with certain signalment, history, or physical examination findings are treated differently than animals without those case characteristics. While clinically reasonable, this practice prevents any attempt to accurately compare alternative risks or treatments.

Similarly, information bias is very common in clinical case management because we intentionally gather different types and amounts of information about different animals. For example, it is reasonable to observe some animals more closely, under different circumstances, or for longer periods of time than other animals. However, this bias can lead to incorrect associations with either disease-causation or treatment factors.


All content from "Because Evidence Matters", the 6th EBVMA Symposium held Friday, 14 November 2014 is © 2014 by the EBVMA (publication) and the author (content) under a Creative Commons Attribution, Non-Commercial, Share-alike, 4.0, International License. Some content may be restricted to active EBVMA members. See our membership page to join or renew or send us an email to membership@ebvma.org. If you're interested in speaking or participating in our AAVSB/RACE accredited continuing education programs, contact us at conference@ebvma.org.

Series Navigation<< Interpreting the results of scientific studies (it’s not black and white)*Small animal consultations: What is the role of the clinical examination? >>