PCA component doesn't matter (from 1 to 5), seems reasonable
z-score seems to give best classification performance, especially when using the mean method to get the instances; when using deconv method, z-scoring doesn't do much.
For block design, getInstance(mean) is better than getInstance(deconv), presumably because deconv is not working very well for short blocks without jitter.
For event-related design, getInstance(mean) is similar to getInstance(deconv). The latter improved presumably because it's easier to estimate single-trial resposne using deconv method in the event-related design.
However, getInstance(deconv) never outperform getInstance(mean), for both block design and event-related design!
Mahalanobis performed badly, almost at chance level.
In absolute terms, classification accuracy is similar for block and event-related designes, ~25% correct.