Effectiveness of the intraday filter trading

In this paper, we study the filter trading rule for intraday trading and explore the problem of finding a suitable filter size based on intraday volatilities. We explore several intraday volatility estimators such as daily range, realized range and realized volatility and study how the filter trading profit for a day with certain volatility depends on the filter size. The bivariate thin plate spline model is used to model the predictor-responsor relationship between the daily volatility, filter size and trading profit. The estimation shows that filter trading rule favors large volatilities in general while the optimal filter size is increasing with the volatility. It also shows that the estimation based on daily range volatility is most reliable among all chosen intraday volatility proxies.