THE EFFICIENCY OF THE SETS AND THE CUSCORE TECHNIQUES UNDER BIASED BASE-LINE RATES

Statistical techniques used for surveillance of disease incidence rate s are generally based on the assumption of known baseline rate of the disease monitored, whereas actually it is an estimate obtained from a large sample, As a result, the time interval until true or false alarm is shorter or longer than assumed. In this study, we evaluate the per formance of the sets and of the cuscore techniques when the estimate o f the baseline rate is biased. We evaluate the effect of an underestim ated baseline rate with respect to frequency of false alarms and to th at of an over estimated rate with respect to the delay until elicitati on of a true alarm. We evaluate the effects of 5 per cent and 10 per c ent bias in the estimated baseline rate for specified conditions assoc iated with sparse data The results show that the effect of plus or min us 5 per cent bias in the estimate are moderate and those of 10 per ce nt we substantial. In general, the effect of an overestimated baseline rate is greater on the sets technique than it is on the cuscore techn ique and the effect of an underestimated rate is greater on the cuscor e technique than it is on the sets technique. However, the differences between the two techniques are small on both perspectives. The two me thods differ also with respect to the expected time until true alarm w hen the specified baseline rate is unbiased. The sets technique is the more efficient in detecting a two-fold increased rate when the number of diagnoses expected annually (E(X)) is less than 1.62, and the cusc ore is the more efficient technique when E(X) > 1.62. We use the term 'turning point' to define the regions in which the sets technique and the cuscore techniques are preferred. With an estimated baseline rate that is 5 per cent higher than the actual rate, the turning point fall s from 1.62 to 1.45 when the rate is twice the baseline rate, and from 5.75 to 4.34 when the rate is triple the baseline rate. (C) 1997 by J ohn Wiley & Sons, Ltd.