Skip to main content
. 2005 Aug;54(8):1121–1125. doi: 10.1136/gut.2004.049460

Figure 1.

Figure 1

 Heterogeneity among the studies. Relative risk of lymphoma against the expected number of cases of lymphoma in each study. The expected number of cases was strongly correlated with total follow up time for the cohort. There was a lower estimated relative risk among large studies and higher estimates among smaller studies.