AN ANALYSIS OF US STOCK-PRICE BEHAVIOR USING WAVELETS

Using wavelets we re-examine the U.S. stock market price index for any evidence of self-similarity or order that might be revealed at differ ent scales. The wavelet transform localized in time can be used to ind icate how the power of the projection of the signal onto the kernel va ries with the scale of observation. By comparing how the local power s cales vary over time much information about the structure of the data can be obtained. Such evidence is not at all evident from standard ana lyses of untransformed data, including projections onto a Fourier basi s. Wavelets can detect structures in data that are highly localized in time and therefore non-detectable by Fourier transforms. The main con clusion is that while the data are clearly complex, there seems to be some evidence of non-randomness in the data. There is also some limite d evidence of quasi-periodicity in the occurrence of large amplitude s hocks to the system.