Abstract:
We establish large deviation principles for the couple of the maximum likelihood estimators of dimensional and drift coefficients in the generalized squared radial Ornstein–Uhlenbeck process. We focus our attention on the most tractable situation, where the dimensional parameter $a$ is greater than $2$ and the drift parameter $b$ is negative $0$. In contrast to the previous literature, we state large deviation principles when both dimensional and drift coefficients are estimated simultaneously.
Keywords:squared radial Ornstein–Uhlenbeck process, maximum likelihood estimates, large deviations.