Figure 5
From: Assessing discriminative ability of risk models in clustered data
![Figure 5](http://media.springernature.com/full/springer-static/image/art%3A10.1186%2F1471-2288-14-5/MediaObjects/12874_2013_Article_1030_Fig5_HTML.jpg)
Center-specific and pooled concordance probability estimates with 95% confidence intervals for Asian centers (external validation). For pooled estimates based on random effects meta-analysis (methods 6 and 8) a 95% prediction interval for the concordance probability is presented by a horizontal line. 1 Equal = Fixed effect meta-analysis with equal weights; 2 Patients = Fixed effect meta-analysis with number of patients as weights; 3 Events = Fixed effect meta-analysis with number of events as weights; 4 Pairs = Fixed effect meta-analysis with number of usable patient pairs as weights; 5 Inv var FE = Fixed effect meta-analysis with inverse variance weights; 6 Inv var RE = Random effects meta-analysis with inverse variance weights; 7 Inv var FE logit = Fixed effect meta-analysis with inverse variance weights on log-odds scale; 8 Inv var RE logit = Random effects meta-analysis with inverse variance weights on log-odds scale.