Hierarchical cluster analysis improves signal-to-noise ratio compared to standard techniques. In this work we present a new approach for improving the SNR in fMRI. The special implementation of the voxel-based motion-correction algorithms allows for very fast and precise correction of head movements in the frame of the selected model. The hierarchical cluster analysis has proven to be a useful tool for the increase of the SNR of the functional results. As these tools and established deterministic and statistical functional analysis tools are implemented in one software platform (FAMIS), direct comparison between the results becomes feasible. As each analysis result can be obtained within seconds and the user can switch between the display for the different results, direct comparison between the methods can be performed. Deterministic analysis leads to an activation concept that is independent from the noise level, and vice versa the statistical analysis leads to an activation concept where the activation is intended as deviation from noise and in such way the activation becomes related to the noise level. The deterministic methods exclude true positive results with increasing noise, and the statistical methods include false positive results with increasing noise. Nevertheless, the decision regarding which of the methods should be the method of choice for fMRI analysis is not the subject of this work.