# Difference in nature of correlation between NASDAQ and BSE indices

**Authors:** P. Manimaran, Prasanta K. Panigrahi, Jitendra. C. Parikh  
**arXiv:** [nlin/0601074](https://arxiv.org/abs/nlin/0601074)  
**Date:** 2006-01-31  
**Summary page:** https://www.summarizepaper.com/en/paper/nlin--0601074v2/

## Key points

- Authors P. Manimaran, Prasanta K. Panigrahi, and Jitendra C. Parikh use wavelet-based approach to study correlation and scaling properties of non-stationary financial time series
- Focus on NASDAQ composite index over 20 years and BSE sensex index over 15 years
- Employ Daubechies family wavelets for detrending
- Significant differences in long-range correlation and fractal behavior between the two indices
- BSE index shows strong non-statistical long-range correlation with Gaussian random noise characteristic after removal
- NASDAQ index displays multifractal behavior with long-range statistical correlation
- Research highlights distinct patterns of correlation and scaling properties in different financial instruments over time
- Valuable insights provided for investors, analysts, and researchers to understand complexities of financial markets

## Summary

In their study, authors P. Manimaran, Prasanta K. Panigrahi, and Jitendra C. Parikh utilize a wavelet-based approach to examine the correlation and scaling properties of non-stationary financial time series. Specifically, they focus on the NASDAQ composite index over a 20-year period and the BSE sensex index over a 15-year period. By employing wavelets from the Daubechies family for detrending purposes, the researchers uncover intriguing insights into the behavior of these stock indices. Their analysis reveals significant differences in long-range correlation and fractal behavior between the two indices. The BSE index exhibits strong non-statistical long-range correlation that, upon removal, exposes a Gaussian random noise characteristic in its fluctuations. In contrast, the NASDAQ index displays multifractal behavior accompanied by long-range statistical correlation. This research sheds light on how different financial instruments can exhibit distinct patterns of correlation and scaling properties over time. By applying advanced wavelet techniques to analyze these non-stationary data sets, the authors provide valuable contributions to understanding the underlying dynamics of stock market movements. Their findings offer valuable insights for investors, analysts, and researchers seeking to better comprehend the complexities of financial markets.