Maximum likelihood estimation for Gaussian processes under inequality constraints
arXiv:1804.03378 · doi:10.1214/19-EJS1587
Abstract
We consider covariance parameter estimation for a Gaussian process under inequality constraints (boundedness, monotonicity or convexity) in fixed-domain asymptotics. We address the estimation of the variance parameter and the estimation of the microergodic parameter of the Matérn and Wendland covariance functions. First, we show that the (unconstrained) maximum likelihood estimator has the same asymptotic distribution, unconditionally and conditionally to the fact that the Gaussian process satisfies the inequality constraints. Then, we study the recently suggested constrained maximum likelihood estimator. We show that it has the same asymptotic distribution as the (unconstrained) maximum likelihood estimator. In addition, we show in simulations that the constrained maximum likelihood estimator is generally more accurate on finite samples. Finally, we provide extensions to prediction and to noisy observations.
References in corpus (6)
- Fixed-domain asymptotic properties of tapered maximum likelihood estimators
- Kriging of financial term-structures
- Calibration and improved prediction of computer models by universal Kriging
- Mixed domain asymptotics for a stochastic process model with time trend and measurement error
- Gaussian Process Modulated Cox Processes under Linear Inequality Constraints
- Semi-parametric estimation of the variogram of a Gaussian process with stationary increments