 This paper presents a new approach for optimizing the window length of steady-state visual evoked potential SSVP based brain-computer interface BCI. This approach is based on analysis of covariance and COVA, which is applied after feature extraction by conventional training free SSVP recognition approaches. The proposed method significantly outperforms the conventional approaches with fixed window in terms of accuracy and information transfer rate, ITR. It is also applicable to various SSVP-based BCI paradigms based on the criterion of significance level without offline analysis to find optimal hyperparameters. This article was authored by Taejun Lee, Sunkyun Nam, and Dongjin Hyun.