Fig. 2
Random-effects meta-analysis of objective response rate comparing weekly and three-weekly docetaxel schedules; squares demonstrate the point estimate of the risk ratio in each study; lines represent the 95% CI; the size of each square is proportional to its weight in meta-analysis; the diamond represents the pooled estimate of the risk ratio after meta-analysis; values < 1 indicate a lower ‘risk’ of response in the weekly arm as opposed to the three-weekly arm while values > 1 indicate a higher ‘risk’ of response in the weekly arm; I2 measure of statistical heterogeneity with the corresponding p-value as test for heterogeneity across studies; τ2 variance of the distribution of the observed study effects