It is a common phenomenon that classification techniques applied to human EEG data are often more successful for some subjects than others. One reason may be that subjects differ in the degree and length of time that they can continue to be engaged with the experimental task at hand. EEG recording can be a time-consuming, tedious and challenging procedure that often involves having subjects remain physically still for extended periods of time while repeatedly performing various mental, computational, imagery or other tasks. Hence, it can be expected that their level of involvement with the task may fluctuate, causing difficulties in using data from the entire task period for classification. This effect is more likely to appear on recordings in which the task period is longer than usual as in the dataset IVa from BCI competition III in which the task time duration is set to 3.5s. This study investigates the impact on classification performance of using data from various fragments of the complete time period. The goal is to improve classification performance by providing higher concentration on some segments than others. The results indicate the importance of focusing on the middle and final sub-epochs, and poorer performance during earlier sub-windows.