RT Journal
A1 Cummings P
T1 MEta-analysis based on standardized effects is unreliable
JF Archives of Pediatrics & Adolescent Medicine
JO Archives of Pediatrics & Adolescent Medicine
YR 2004
FD June 1
VO 158
IS 6
SP 595
OP 597
DO 10.1001/archpedi.158.6.595
UL http://dx.doi.org/10.1001/archpedi.158.6.595
AB 
Meta-analysis is a quantitative method of summarizing the results of several studies. One goal of meta-analysis is to estimate the size of the pooled association between a treatment or exposure and an outcome. This pooled association, or effect can be used to judge the clinical or public health impact of the exposure. A second goal is to seek evidence that the association varies according to the level of some other factor. This is often done using formal statistical tests of the hypothesis that the associations in the different studies are similar (homogeneous). A third goal is to estimate a variance so that the precision of the pooled association estimate may be judged using a confidence interval.