ERROR: You cannot have an empty box in the calculation. You can only have a zero number in the drop out box (e)

HELP: If you would like help in completing the sample size calculation click help off. Help Off

1) Determine what effect size you would like to detect: box (a)

For example a trial is being designed to compare two treatments to reduce blood pressure. It is decided that a clinically meaningful difference (effect size) is 5mmHg, i.e. the trial is designed to detect a difference between two treatments of 5mmHg in the reduction in blood pressure. E.g. the two groups may show a mean change in BP of 6mmHg in the test group and 1mmHg in the comparator group. In this example the number in box (a) would be 5

2. Determine the significance level: box (b)

This is usually set at 5% so box (c) would be 5. In simple terms this is the acceptable chance of the trial showing a false positive, in other words demonstrating a difference between the treatments when there isn't really one there. The value set here is what the p-value must be less than at the end of the trial to declare a significant difference. If in doubt just leave it at 5% and think no more of it!

3. Standard Deviation of Outcomes: box (c)

With continuous data there is the need to include a measure of variability in the sample size calculation. This is done by introducing the standard deviation. In box (c) put the expected standard deviation of the outcome variable. This can be obtained from previous trials, reports, publications etc. Make sure that you include the standard deviation rather than a standard error as the latter will give an incorrectly lower sample size.

4. Determine the Power Level: box (d)

In simple terms power is the chance of the trial demonstrating a significant difference if the assumed values in box (a) and (b) are correct. If the assumed values (a) and (b) are incorrect then the power will not be what is stated. Most trials are conducted with 80% or 90% power. For 80% power put 80 in box (d)

5. Determine the Withdrawal/Non-evaluable Rate: box (e).

The sample size calculator will initially determine how many subjects are required to complete the trial (and appear in the final analysis). A percentage of patients will usually not complete the trial and therefore will not contribute to the final analysis. If you expect that 10% of your subjects may do this then put 10 in box (e)