Rescaled range

From Wikipedia, the free encyclopedia
Jump to: navigation, search

The rescaled range is a statistical measure of the variability of a time series introduced by the British hydrologist Harold Edwin Hurst (1880–1978).[1] Its purpose is to provide an assessment of how the apparent variability of a series changes with the length of the time-period being considered.

The rescaled range is calculated from dividing the range of the values exhibited in a portion of the time series by the standard deviation of the values over the same portion of the time series. For example, consider a time series {2, 5, 3, 7, 8, 12, 4, 2} which has a range, R, of 12 - 2 = 10. Its standard deviation, s, is 3.46, so the rescaled range is R/s = 2.71.

If we consider the same time series, but increase the number of observations of it, the rescaled range will generally also increase. The increase of the rescaled range can be characterized by making a plot of the logarithm of R/s vs. the logarithm of n. The slope of this line gives the Hurst exponent, H. If the time series is generated by a random walk (or a Brownian motion process) it has the value of H =1/2. Many physical phenomena that have a long time series suitable for analysis exhibit a Hurst exponent greater than 1/2. For example, observations of the height of the Nile River measured annually over many years gives a value of H = 0.77.

Several researchers (including Peters, 1991) have found that the prices of many financial instruments (such as currency exchange rates, stock values, etc.) also have H > 1/2.[2] This means that they have a behavior that is distinct from a random walk, and therefore the time series is not generated by a stochastic process that has the nth value independent of all of the values before this. This is referred to as long memory. However this result is controversial and several studies using Lo's [3] modified rescaled range statistic have contradicted Peters' results.

Calculation[edit]

The Rescaled Range is calculated for a time series, X=X_1,X_2,\dots, X_n \, , as follows:[4]
  1. Calculate the mean
    m=\frac{1}{n} \sum_{i=1}^{n} X_i \,
  2. Create a mean adjusted series
    Y_t=X_{t}-m \text{  for } t=1,2, \dots ,n \,
  3. Calculate the cumulative deviate series Z;
    Z_t= \sum_{i=1}^{t} Y_{i}  \text{  for }  t=1,2, \dots ,n \,
  4. Create a range series R;
     R_t = \max\left (Z_1, Z_2, \dots, Z_t  \right )- \min\left (Z_1, Z_2, \dots, Z_t  \right ) \text{  for } t=1,2, \dots, n \,
  5. Create a standard deviation series S;
    S_{t}= \sqrt{\frac{1}{t} \sum_{i=1}^{t}\left ( X_{i} - u \right )^{2}}  \text{  for } t=1,2, \dots ,n \,
    Where u is the mean for the time series values X_1,X_2, \dots, X_t \,
  6. Calculate the rescaled range series (R/S)
    \left ( R/S \right )_{t} = \frac{R_{t}}{S_{t}} \text{  for } t=1,2, \dots, n \,

Lo (1991) advocates adjusting the standard deviation S for the expected increase in range R resulting from short-range autocorrelation in the time series.[3] This involves replacing S by  \hat{S} , which is the square root of

 \hat{S}^2 = S^2 + 2 \sum_{j=1}^{q} \left( 1 - \frac{j}{q + 1} \right) C(j),

where q is some maximum lag over which short-range autocorrelation might be substantial and C(j) is the sample autocovariance at lag j. Using this adjusted rescaled range, he concludes that stock market return time series show no evidence of long-range memory.

See also[edit]

References[edit]

  1. ^ Hurst, H. E. (1951). "Long term storage capacity of reservoirs". Trans. Am. Soc. Eng. 116: 770–799. 
  2. ^ Peters, E. E. (1991). Chaos and order in the capital markets. John Wiley and Sons. ISBN 0-471-53372-6. 
  3. ^ a b Lo, A. (1991). "Long-Term Memory in Stock Market Prices". Econometrica 59: 1279–1313. doi:10.2307/2938368. 
  4. ^ Bo Qian; Khaled Rasheed (2004). "HURST EXPONENT AND FINANCIAL MARKET PREDICTABILITY". IASTED conference on "Financial Engineering and Applications"(FEA 2004). pp. 203–209. CiteSeerX: 10.1.1.137.207. 

Further reading[edit]