Data imputation in switchback designs using a mixed model with correlated errors.
Development of the kriging method with application
This paper describes a modification of the kriging method for working with the square root transformation of a spatial random process. We have developed this method for the situation where the spatial process observed is not supposed to be stationary but the assumption is that its square root is a second order stationary spatial random process. Consequently this method is developed for estimating the integral of the process observed and finally some application of the method is given to data from...
Discrete time nonlinear filters with informative observations are stable.
Discrimination between nonstationary and nearly nonstationary processes, and its effect on forecasting
Discrimination between nonstationary and nearly nonstationary processes, and its effect on forecasting
Dynamic credibility with outliers and missing observations
In actuarial practice the credibility models must face the problem of outliers and missing observations. If using the -estimation principle from robust statistics in combination with Kalman filtering one obtains the solution of this problem that is acceptable in the numerical framework of the practical actuarial credibility. The credibility models are classified as static and dynamic in this paper and the shrinkage is used for the final ratemaking.