Functional magnetic resonance imaging (FMRI) has been widely used in the field of medicine and physiology, which realizes neuro imaging without damage. FMRI was initially applied to the analysis of FMRI images; however, its statistical analysis was limited to the elementary processes because of the complexities of the FMRI images and the difficulties to establish the neuromotor time–space model. In this chapter, we focus on the analysis of FMRI images based on large data. Firstly, we make the time-correlation analysis of the data to reduce the size of the data. Then, we further investigate the spatial characteristics of valid signals, and compare the predicted signal and the original signal in the time domain and frequency domain. We find that there is a strong relevance of FMRI data in both time and space area, which indicates that the stimulation signal of the brain radiates to the surroundings of the stimulated point, and the signal is continuous in time, not an impulse.