Rescaled Range Analysis
A statistical analysis of a time-series of financial data that attempts to find patterns that might repeat in the future. While rescaled-range analysis techniques have proved useful in other mathematical endeavors, the evidence for its use in analyzing financial data remains somewhat unproven. There are two main variables used in this technique – the range of the data (as measured by the highest and lowest values in the time period), and the standard deviation of the data. A derivative of this mathematical result is known as a Hurst exponent; if a trend actually exists in the data, this Hurst exponent can extrapolate a future value or average for the data point. Investopedia Says:
The desire to predict patterns in financial data (especially asset prices) is as old as the history of data itself. What makes the search so appealing is that stock market history does show cyclicality, albeit in a non-periodic way. Business cycle lengths seem to keep showing up in periods of four to five years, although nobody can explain why. Related Terms:
Business Cycle
Cyclical Stock
Homoskedastic
Regression
Standard Deviation
Statistics |