Cent Eur J Public Health 2011, 19(2):118-120 | DOI: 10.21101/cejph.a3581

Publication Bias in Epidemiological Studies

Nazish Siddiqi

Department of Epidemiology, Michigan State University, East Lansing, Michigan, USA

Communication of research findings is the utmost responsibility of all scientists. Publication bias occurs if scientific studies with negative or null results fail to get published. This can happen due to bias in submitting, reviewing, accepting, publishing or aggregating scientific literature that fails to show positive results on a particular topic. Publication bias can make scientific literature unrepresentative of the actual research studies. This can give the reader a false impression about the beneficial effects of a particular treatment or intervention and can influence clinical decision making. Publication bias is more common than it is actually considered to be, but there are ways to detect and prevent it. This paper comments on the occurrence, types and consequences of publication bias and the strategies employed to detect and control it.

Klíčová slova: bias, publication bias, epidemiological studies, funnel plot, trim and fill method

Vloženo: 25. srpen 2009; Revidováno: 25. květen 2011; Přijato: 25. květen 2011; Zveřejněno: 1. červen 2011  Zobrazit citaci