Since we were unable to verify if an email was received and read, the true response rate is likely higher, but we cannot confirm this.
Makuch and Simon gave a sample size calculation formula for historical control (HC) studies that assumed that the observed response rate in the control group is the true response rate.
We conclude that it is relevant to consider optimal designs under a range of hypotheses about the true response rate, and that allowing early stopping for efficacy is always advantageous in terms of expected sample size.
The 241 respondents constitute a "true response rate" of "between 20 to 25percentthe the authors write; "a response rate of less than 25percentt is typical for robust, web-based, academic-quality surveys," they add.
The chapter explores whether or not it is possible to design a study with enough patients at a dose level to ensure with high probability that after observing the responses one can be 90% confident that the true response rate is greater than some specified level.
It is possible that the true response rate to this survey was as high as 60%.
Based on these acceptance criteria, power calculations were conducted assuming the true response rate of 70% and 80% with sample sizes of 90, 120 and 150.
Furthermore, we assumed a true response rate of 50%.
This design precludes measurement of the true response rate.
But does this really represent the true response rate?
This design required 44 patients to test the null hypothesis that the true response rate was ⩽5% vs the alternative hypothesis that the true response rate was ⩾15%.
