
Accession Number : ADA181184
Title : MEstimation for Nearly NonStationary Autoregressive Time Series.
Descriptive Note : Technical rept.,
Corporate Author : WASHINGTON UNIV SEATTLE DEPT OF STATISTICS
Personal Author(s) : Cox,Dennis D ; Llatas,Isabel
PDF Url : ADA181184
Report Date : Mar 1987
Pagination or Media Count : 43
Abstract : The nearly nonstationary first order autoregression is a sequence of processes where the autoregressive coefficient tends to 1 as n approaches infinity. Mestimates of the autoregressive coefficient are considered. The process is allowed to be nongaussian, but a 2 + delta moment condition is assumed. The limiting distribution is not the usual normal limit but is characterized as a ratio of two stochastic integrals. The asymptotically most efficient Mestimate is not given by maximum likelihood. However, it is shown that the loss of efficiency in using maximum likelihood is no worse than about 20% whereas the usual least squares estimator can have arbitrarily low efficiency. Keywords: M estimation; time series, autoregressive; non stationary.
Descriptors : *TIME SERIES ANALYSIS, AUTOMATIC, DISTRIBUTION, EFFICIENCY, ESTIMATES, LIMITATIONS, RATIOS, REGRESSION ANALYSIS, SERIES(MATHEMATICS), COEFFICIENTS, OPTIMIZATION, SEQUENCES(MATHEMATICS)
Subject Categories : Statistics and Probability
Distribution Statement : APPROVED FOR PUBLIC RELEASE