The bulk of the stock market correlation matrix is not pure noise

@article{citeulike:575403, abstract = {We analyse the structure of the distribution of eigenvalues of the stock market correlation matrix with increasing length of the time series representing the price changes. We use 100 highly capitalized stocks from the American market and relate the result to the corresponding ensemble of Wishart random matrices. It turns out that systematically more eigenvalues remain beyond the borders prescribed by this variant of the random matrix theory (RMT). This may indicate that even the bulk of the spectrum of the stock market correlation matrix carries some sort of correlations that are masked by a measurement noise when the time series used to construct the matrix are short. We also study some other characteristics of the "noisy" eigensignals, like their return distributions, temporal correlations or their multifractal spectra, and the results support the above conclusions.}, author = {Kwapien, J. and Drozdz, S. and Oswie[spacing}, citeulike-article-id = {575403}, doi = {10.1016/j.physa.2005.05.090}, journal = {Physica A: Statistical Mechanics and its Applications}, keywords = {matrix, random}, month = {January}, pages = {589--606}, posted-at = {2006-04-04 11:44:04}, priority = {2}, title = {The bulk of the stock market correlation matrix is not pure noise}, url = {http://dx.doi.org/10.1016/j.physa.2005.05.090}, volume = {359}, year = {2006} }

TY - JOUR ID - citeulike:575403 L3 - citeulike-article-id:575403 TI - The bulk of the stock market correlation matrix is not pure noise JF - Physica A: Statistical Mechanics and its Applications VL - 359 SP - 589 EP - 606 N2 - We analyse the structure of the distribution of eigenvalues of the stock market correlation matrix with increasing length of the time series representing the price changes. We use 100 highly capitalized stocks from the American market and relate the result to the corresponding ensemble of Wishart random matrices. It turns out that systematically more eigenvalues remain beyond the borders prescribed by this variant of the random matrix theory (RMT). This may indicate that even the bulk of the spectrum of the stock market correlation matrix carries some sort of correlations that are masked by a measurement noise when the time series used to construct the matrix are short. We also study some other characteristics of the "noisy" eigensignals, like their return distributions, temporal correlations or their multifractal spectra, and the results support the above conclusions. KW - matrix KW - random AU - Kwapien, J AU - Drozdz, S AU - Oswie[spacing PY - 2006/01/01/ UR - http://dx.doi.org/10.1016/j.physa.2005.05.090 ER -