Advancing the iid Test Based on Integration across the Correlation Integral: Ranges, Competition, and Power

This paper builds on Kocenda (2001) and extends it in two ways. First, two new intervals of the proximity parameter epsilon (over which the correlation integral is calculated) are specified. For these epsilon-ranges new critical values for various lengths of the data sets are introduced and through Monte Carlo studies it is shown that within new epsilon-ranges the test is even more powerful than within the original epsilon-range. A sensitivity analysis of the critical values with respect to epsilon-range choice is also given. Second, a comparison with existing results of the controlled competition of Barnett et al. (1997) as well as broad power tests on various nonlinear and chaotic data are provided. The results of the comparison strongly favor our robust procedure and confirm the ability of the test in finding nonlinear dependencies. An empirical comparison of the new epsilon-ranges with the original one shows that the test within the new epsilon-ranges is able to detect hidden patterns with much higher precision. Finally, new user-friendly and fast software is introduced.