A couple of studies have been conducted with able-bodied subjects and/or arm amputees to investigate the impact of arm position changes in the practical use of a multifunctional myoelectric prosthesis. The classification accuracy calculated offline from electromyography (EMG) recordings was used as a performance metric in these studies, which is not a true measure of real-time control performance. In this study, the influence of arm position changes on the real-time performance of EMG pattern recognition (EMG-PR) control was quantitatively evaluated with four real-time metrics including motion response time, motion completion time, motion completion rate, and dynamic efficiency. Ten able-bodied subjects participated in the study and a cascade classifier built with both EMG and mechanomyogram (MMG) recordings was proposed to reduce the impact of arm position variation. The pilot results showed that arm position changes would substantially affect the real-time performance of EMG pattern-recognition based prosthesis control. Using a cascade classifier could significantly increase the average real-time completion rate (p-value<0.01). This suggests that the proposed cascade classifier may have potential to reduce the influence of arm position variation on the real-time control performance of a prosthesis.