The results are supplied through graphs showing the observedrelative frequencies of the disease states per week and future pre-dictions. Each proportion includes 95% confidence intervals as errorbars. The confidence intervals can be used as an indirect mea-sure of significance among weeks or groups (Du Prel et al., 2009).Confidence intervals that do not overlap are an indication for astatistically significant difference in proportions. If the confidenceintervals overlap, the difference in proportion is not statisticallysignificant. The proportions and predictions are also available intable form under each graph.