INVARIANT ESTIMATION OF STOCHASTIC SYSTEM PARAMETERS.
POLYTECHNIC INST OF BROOKLYN N Y MICROWAVE RESEARCH INST
Pagination or Media Count:
The report is concerned with the estimation of the statistics of a class of random processes. Properties of a new constant risk estimator of the autocorrelation function for exponentially correlated processes are studied analytically. The results are applied to computer-generated random processes and the estimates found are compared with the results of more common estimation methods, such as autoregressive estimation. The effect of increasing the amount of data and changing the input distribution is examined both analytically and experimentally. Author
- Statistics and Probability