New Zealand Dollar (NZD) LIBOR: technical predictability overview - NZD LIBOR autocorrelations

User Rating: / 5
PoorBest 
Written by Forex Automaton   
Monday, 22 December 2008 14:44
Article Index
New Zealand Dollar (NZD) LIBOR: technical predictability overview
NZD LIBOR volatility
NZD LIBOR autocorrelations
Correlations between NZD LIBOR maturities, s/n-o/n and longer terms
Correlations between NZD LIBOR maturities, 1-week and longer terms
Correlations between NZD LIBOR maturities, 1-month and longer terms
Correlations between NZD LIBOR maturities, 3-month and longer terms
All Pages

LIBOR autocorrelations

Fig.3 and subsequent figures ascertain the significance of the patterns by comparing with the statistical noise estimate, based on simulations devoid of correlations, but with volatility of the actual data.

A few basic facts about autocorrelations may help interpreting the plots:

  • A positive autocorrelation in returns, associated with a certain time lag, means that you can bet that the current trend (be it up or down) will continue at the moment separated from now by that time lag.
  • A negative autocorrelation in returns means the opposite -- that a trend reversal is likely over that time lag.
  • Thus, the autocorrelation of a wave -- a highly predictable pattern -- looks like a wave.
  • The positive peak at zero lag by itself tells you nothing useful for prediction -- its magnitude is a measure of volatility.

 

The s/n-o/n and 1-week plots show a peculiar short-range pattern of a "damped oscillation" in the vicinity of zero lag, with perhaps a 10-day period. The autocorrelaitons for 3-month, 6-month and 12-month LIBOR have a similar pattern, but with a much longer period, about 30 days.

NZD s/n-o/n LIBOR autocorrelation, 1 day time scale NZD 1-week LIBOR autocorrelation, 1 day time scale NZD 1-month LIBOR autocorrelation, 1 day time scale NZD 3-month LIBOR autocorrelation, 1 day time scale NZD 6-month LIBOR autocorrelation, 1 day time scale NZD 12-month LIBOR autocorrelation, 1 day time scale

Fig.3:Autocorrelation of logarithmic returns in the historical NZD LIBOR is shown against the backdrop of statistical "noise". The noise is obtained from martingale simulations based on the historical volatilities of LIBOR for the period under study. The noise is presented as mean plus-minus 1 RMS, where RMS characterizes the distribution of the correlation value obtained for each particular time lag bin by analyzing 20 independent simulated uncorrelated time series. The RMS is a measure of accuracy in the determination of the correlation values, an irreducible uncertainty dependent on the amount of data and the time scale. Top to bottom: s/n-o/n, 1-week, 1-month, 3-month, 6-month, and 12-month data.



Last Updated ( Monday, 14 September 2009 17:01 )