Overview for Power and Sample Size for Equivalence Test with Paired Data

Use Power and Sample Size for Equivalence Test with Paired Data to examine the relationship between power, sample size, and difference when you want to evaluate the equivalence between a test mean and a reference mean using paired observations.

Use these calculations for the following reasons:

Before you collect data for an equivalence test with paired data, to ensure that your design has an adequate sample size to achieve acceptable power
After an equivalence test with paired data, to improve the design for the next study

The paired equivalence test is useful for analyzing a set of dependent observations, such as the same set of items that were measured under two different conditions, or before-and-after measurements of the same person.

For example, an engineer for a vision care company wants to determine whether a new cleaning solution for contact lenses is as effective as the leading brand. The engineer recruits 14 participants for the study. Each participant will use a different cleaning solution on the contact lens in each eye. The engineer will measure the residual film on each contact lens of each person, which will create paired observations. Before the engineer collects the data for the equivalence test with paired data, she uses a power and sample size calculation to determine whether a sample size of 14 provides adequate power for the test.

Where to find this analysis

To perform a power and sample size calculation for an equivalence test with paired data, choose Stat > Power and Sample Size > Equivalence Tests > Paired.

When to use an alternate analysis

If the observations in your sample are independent and are not matched samples, use Power and Sample Size for 2-Sample Equivalence Test instead. For more information, go to How are dependent and independent samples different?.