Hyperscanning approaches represent a shift from single- to two-person neuroscience, enabling a more profound understanding of the neural mechanisms underlying interpersonal synchronization. In this context, fNIRS has emerged as a valuable tool for measuring brain activity in a natural, unconstrained environment. While interpersonal synchrony using fNIRS hyperscanning has been well studied using statistical association analysis, establishing causal relationships that elucidate the direction of influence remains challenging. This study aimed to investigate the feasibility of testing the direction of influence in dyadic interactions. Since the ground truth of such direction is not available in a natural setting, we validated our approach in an experimental setup in which we controlled the direction of influence between two subjects by assigning them the roles of ’Model’ and ’Imitator’ of specified motor tasks. A total of 22 participants, hence 11 dyads, completed the task in a within-subject design. We adapted concepts from spectral causal-effect decomposition theories to formulate a new measure of the direction and intensity of influence. The results of this study demonstrate that the direction of influence in the fNIRs data of motor tasks can be detected with an Accuracy in the range of 69-88%. Furthermore, the proposed spectral causality measure was shown to significantly reduce spurious causal relationships due to the confounding effects of physiological processes and measurement artifacts compared to time-domain causal analysis.