One of the most common operations performed on market data is a smoothing, low-pass FIR (Finite Impulse Response) filtering, which enables us to obtain less noisy data. Such a filtering, however, results in delaying and distorting output data. Both, high noise-content in original input data, and delay and distortion in output data have a negative impact on attempts of predicting further market movements or attaining positive returns from investments. Therefore, it is important to choose the appropriate filter impulse response to obtain a reasonable tradeoff between the delay and distortion on one hand, and the smoothness of output data on the other hand. The goal of this contribution is to compare commonly used FIR filters impulse response, by using approximation theory based norms for the following output parameters: delay, correlation between input and output signal, and smoothness of the output signal. The comparison is made for two classes of the impulse response shape, i.e., symmetric (even function), and asymmetric one. In the first case the focus is on the minimum of distortion i.e., maximum correlation between input and output signal vs. smoothness of the output signal. In the asymmetric case the main goal is to attain a minimum delay between filter output and input signal. Nine cases of impulse response are considered, namely rectangular, triangular, Hanning, Hamming, Blackman, and four Chebyshev windows. One-minute quotations for the futures contracts on WIG 20, Warsaw Stock Exchange index, covering period of time from October 30,2001 thru June 16, 2003, (ca. 145000 samples), has been used for the computations. The results indicate that the most commonly used filter of rectangular impulse response shape is not necessarily the best choice, and that depending upon assumed performance criteria other filters would perform better.

• Legal notice:
  

  Copyright (c) Pielaszek Research, all rights reserved.
  The above materials, including auxiliary resources, are subject to Publisher's copyright and the Author(s) intellectual rights. Without limiting Author(s) rights under respective Copyright Transfer Agreement, no part of the above documents may be reproduced without the express written permission of Pielaszek Research, the Publisher. Express permission from the Author(s) is required to use the above materials for academic purposes, such as lectures or scientific presentations.
  In every case, proper references including Author(s) name(s) and URL of this webpage: https://science24.com/paper/2463 must be provided.

1. Cycles in DJIA
2. Spectral analysis of capital markets
3. Emotional feedback in capital markets due to trader attitude
4. Non-causal FIR filters for the maximum return from capital markets