Ship response prediction is one of the emerging interests in seakeeping, given the extensive range of applications for autonomous control of marine vehicles. In particular, the shortterm prediction and online updates of the ship response have been in the practical attention span. Despite a body of studies on different predictors, the asymptotic properties of estimators concerning the time series sample size have not been addressed specifically. The predictors only have been analysed for a fixed observation window regardless of the intrinsic statistical characteristics obtainable in the time series. To this end, the current research has considered the performance of two nonlinear and linear based regressors: support vector regression (SVR) and the adaptive Seasonal Auto-Regressive and Integrated Moving Average (SARIMA) model on the time series data obtained from a simulated semisubmersible platform in different sea states. The experiment demonstrated that the prediction accuracy highly depends on the observation window length with respect to the statistical properties of the responses in various wave conditions. Therefore, an innovative filter using the weighted average of the proposed functions has been introduced to dynamically adjust the buffer window based on the signal statistical characteristics. The promising results showed that the filter not only could contribute to promoting any predictors used in autonomous onboard decision-making, guidance, and stabilization systems for present and future intelligent onboard control systems, but the proposed mechanism can be employed in dynamic systems in other disciplines too.