Wireless mobile ad hoc network experimentation is subjected to stochastic factors from the radio environment and node mobility. To achieve test repeatability and result reproducibility such stochastic factors need to be controlled or assessed in order to obtain conclusive results. This has implications on the design of testbeds. We present a methodology that addresses repeatability and describe how it has guided us in the design of our Ad hoc Protocol Evaluation (APE) testbed. Finally, by using APE, we present side-by-side routing protocol comparison results and show a radio phenomena that is not visible in simulations.