Meta-Analysis in Epidemiology

摘要: The use of meta-analyses in order to synthesise the evidence from epidemiological studies has become more and popular recently. It been estimated by Egger et al. (1998) that articles retrieved MEDLINE with medical subject heading (MeSH) term “meta-analysis” some 33% reported results a meta-analysis randomised clinical trials nearly same proportion (27%) were observational studies, including 12% papers which aetiology disease was investigated. remaining include methodological publications or review articles. Reasons for popularity are growing information scientific literature need timely decisions risk assessment public health. While methods summarise controlled have continuously developed during last years, now summarised several text books example Sutton (2000), Whitehead (2002) handbook (2001), Dickersin argued statistical still behind comparison progress made trials. research caused many controversial discussions, see Blettner (1999), Berlin (1995), Greenland (1994), Feinstein Olkin Shapiro (1994a,b) Weed (1997) detailed overview arguments.