Nine Parkinson's disease (PD), seven olivopontocerebellar atrophy (OPCA) patients and two age-matched control groups learned a linear arm movement-scaling task over 2 days, requiring movements proportional in length to visually presented target-bars. Scaling was acquired through knowledge of results (KR concerning the direction and magnitude of errors) following every second acquisition trial. Initial acquisition of both groups was significantly worse than their respective controls (poorer movement scaling), but rapidly improved to nearly identical levels. Retention for the PD group's movement scaling was as good as controls initially, but markedly poorer after 24 h. The OPCA group did not show this deficit. Both patient groups extrapolated accurately to longer, previously unpracticed target distances (no KR provided), suggesting an unimpaired capacity to generate and use an internal representation of the movement scaling. They also rapidly learned a new scaling relationship when the gain was changed. Overall, the learning of this movement-scaling task was not adversely affected in OPCA, and the impairment was restricted primarily to longer-term retention in PD. The study suggests that: (1) the ability to acquire movement scaling in a task that requires conscious use of error feedback and no new coordination may depend little on the cerebellum, and (2) the basal ganglia may participate in longer-term storage of scaling information.