Modeling Nonstationary Random Processes with an Application to Gyro Drift Rate

The problem of estimating the a priori statistics of a nonstationary process is considered using finite-time averages of experimental data. A model of the form of a linear time-invariant difference equation with a stationary independent random sequence driving function is proposed and investigated. Finite-time averages are calculated and then used in a steepest descent method to determine the coefficients of the difference nce equation. Methods are presented for transforming this model to the statespace pace format necessary for Kalman filtering, and an example is given using actual gyro drift-rate data.