Advances in Risk Management

RICCARDO BRAMANTE AND GIAMPAOLO GABBI 227

0,250

0,250

0,200

0,200

0,150

0,150

0,100

0,100

0,050

0,050

0,000

Daily correlation change

50 99 148 197 246 295 344 393 442 491 540

Number of observations  558 daily changes

No. of observations

1

Figure 12.1Distribution function of jumps EUR–USD, 2003–05

0,400

0,300

0,200


0,300


0,400

0,200

0,100

0,100

0,000

50 99 148 197 246 295 344 393 442 491 540

Number of observations  558 daily changes

No. of observations

Daily correlation change

1

Figure 12.2Distribution function of jumps EUR–JPY, 2003–05

volatilities is through the method of exponentially weighted daily histor-
ical observations with a decay factor of 0.94. The complete time series is
recorded from 1 January 2003 to 30 September 2005 consisting of 687 data
points: 558 of them, until 31 March 2005, were used for historical model
estimation whereas the remaining ones were used for out of sample testing.
From these data we computed all the variations, from positive to negative.
Figures 12.1 to 12.3 depict the distribution function of correlation jumps in
all the markets considered.