protected void initArrays(int d) {
double dt;
for (int j = 0; j < d; j++) {
dt = t[j + 1] - t[j];
alphadt[j] = alpha * (dt);
sigmasqrdt[j] = sigma * Math.sqrt(dt);
}
}
// This is called by setObservationTimes to precompute constants
// in order to speed up the path generation.
protected void init() {
super.init();
mudt = new double[d];
sigmasqrdt = new double[d];
for (int j = 0; j < d; j++) {
double dt = t[j + 1] - t[j];
mudt[j] = mu * dt;
sigmasqrdt[j] = sigma * Math.sqrt(dt);
}
}
/**
* Generates and returns the next observation at time @f$t_{j+1} =@f$ `nextTime`. Assumes the
* previous observation time is @f$t_j@f$ defined earlier (either by this method or by
* <tt>setObservationTimes</tt>), as well as the value of the previous observation @f$X(t_j)@f$.
* *Warning*: This method will reset the observations time @f$t_{j+1}@f$ for this process to
* `nextTime`. The user must make sure that the @f$t_{j+1}@f$ supplied is @f$\geq t_j@f$.
*/
public double nextObservation(double nextTime) {
double previousTime = t[observationIndex];
double xOld = path[observationIndex];
observationIndex++;
t[observationIndex] = nextTime;
double dt = nextTime - previousTime;
double x = xOld + alpha * (beta - xOld) * dt + sigma * Math.sqrt(dt) * gen.nextDouble();
path[observationIndex] = x;
return x;
}
/**
* Generates and returns the next observation at time @f$t_{j+1} =@f$ `nextTime`. It uses the
* previous observation time @f$t_j@f$ defined earlier (either by this method or by
* <tt>setObservationTimes</tt>), as well as the value of the previous observation @f$X(t_j)@f$.
* *Warning*: This method will reset the observations time @f$t_{j+1}@f$ for this process to
* `nextTime`. The user must make sure that the @f$t_{j+1}@f$ supplied is @f$\geq t_j@f$.
*/
public double nextObservation(double nextTime) {
// This method is useful for generating variance gamma processes
double x = path[observationIndex];
double previousTime = t[observationIndex];
observationIndex++;
t[observationIndex] = nextTime;
double dt = nextTime - previousTime;
x += mu * dt + sigma * Math.sqrt(dt) * gen.nextDouble();
path[observationIndex] = x;
return x;
}
/**
* Generates an observation of the process in `dt` time units, assuming that the process has
* value @f$x@f$ at the current time. Uses the process parameters specified in the constructor.
* Note that this method does not affect the sample path of the process stored internally (if
* any).
*/
public double nextObservation(double x, double dt) {
x += mu * dt + sigma * Math.sqrt(dt) * gen.nextDouble();
return x;
}
/**
* Generates and returns an observation of the process in `dt` time units, assuming that the
* process has value @f$x@f$ at the current time. Uses the process parameters specified in the
* constructor. Note that this method does not affect the sample path of the process stored
* internally (if any).
*/
public double nextObservation(double x, double dt) {
x = x + alpha * (beta - x) * dt + sigma * Math.sqrt(dt) * gen.nextDouble();
return x;
}