Testing whether a time series is Guassian

Thesis/Dissertation · Tue Jan 01 04:00:00 EST 1991

OSTI ID:7173600

Lee, S

The authors first tests whether a stationary linear process with mean 0 is Gaussian. For the invertible processes, he considers the empirical process based on the residuals as the basis of a test procedure. By applying the result of Boldin (1983) and Kreiss (1988), he shows that the process behaves asymptotically like the one based on the true errors. For non-invertible processes, on the other hand, Lee uses the empirical process based on data themselves rather than the one based on residuals. Here, the time series is assumed to be a strongly mixing process with a suitable mixing order. Then, the asymptotic behavior of the empirical process in each case is studied under a sequence of contiguous alternatives, and quadratic functionals of the empirical process are employed for AAR([infinity]) processes in order to compare efficiencies between these two procedures. The rest of the thesis is devoted to extending Boldin's results to nonstationary processes such as unstable AR(p) processes and explosive AR(1) processes, analyzing by means of a general stochastic regression model.

• Research Organization: Maryland Univ., College Park, MD (United States)
• OSTI ID: 7173600
• Country of Publication: United States
• Language: English

Related Subjects

99 GENERAL AND MISCELLANEOUS
990200* -- Mathematics & Computers
ASYMPTOTIC SOLUTIONS
GAUSSIAN PROCESSES
MATHEMATICS
REGRESSION ANALYSIS
STATISTICS
STOCHASTIC PROCESSES
TIME-SERIES ANALYSIS