摘要:An increasing number of quantitative reviews of epidemiological data includes a doseresponse analysis. Aims of this paper are to describe the main aspects of the methodology and to illustrate the novel R package dosresmeta developed for multivariate dose-response meta-analysis of summarized data. Specific topics covered are reconstructing covariances of correlated outcomes; pooling of study-specific trends; flexible modeling of the exposure; testing hypothesis; assessing statistical heterogeneity; and presenting in either a graphical or tabular way the overall dose-response association.