70 Per-protocol patients Plan to recruit 70 evaluable patients (With expected dropout rate of 22%, the sample size would be 90 subjects.) Simon's two-stage design (Simon, 1989) will be used. The null hypothesis that the true response rate is 0.45 will be tested against a one-sided alternative. In the first stage, 42 patients will be accrued. If there are 19 or fewer responses in these 42 patients, the study will be stopped. Otherwise, 28 additional patients will be accrued for a total of 70. The null hypothesis will be rejected if 39 or more responses are observed in 70 patients. This design yields a type I error rate of 0.05 and power of 0.8 when the true response rate is 0.6.
