Table 1 Statistical power (Lea-Coulson model)
p × 1081.251.51.752.02.53.0
LR test11.
C.I. overlap10.524.744.962.488.797.5
  • Six groups of simulated experiments were compared with a baseline group. The mutation rate in the baseline group 1.0 × 10−8 is smaller than the mutation rates in the six other groups. The final cell population size Embedded Image in the baseline group is twice as large as in the other groups. Three comparison methods, namely, the LRT, the method of checking C.I. overlapping, and the asymptotic normality method, were used to test for equality of mutation rates between experiments in the baseline group and experiments from one of the other six groups. Each entry in the table is the percentage of tests that are significant at the 0.05 level. Hence, each entry is an estimate of statistical power at the 0.05 level.