Monte Carlo Techniques for Estimating Power in Aircraft T&E Tests

Edwards AFB, as a matter of policy, requires statistical rigor be a part of test design and analysis. Statistically defensible methods are used to gain as much information as possible from each test. This requires Statistically defensible methods be identified and applied to each test Setting up tests to maximize scope of inference, and Determining the power or each test to optimize sample size. This paper demonstrates how Monte Carlo techniques may be applied to aircraft test and evaluation to determine the power of the test and the associated sample size requirements. Traditional methods for determining the power of a test are based on distributional assumptions associated with data. These assumptions may not be appropriate a distribution-free Monte Carlo technique for power assessment for tests with possible serially correlated data is presented. The technique is illustrated with an example from a target location error TLE test. Power of the test and appropriate sample sizes are derived using Monte Carlo simulation implemented in R.