Open Access
September, 1982 Analysis of Time Series from Mixed Distributions
P. M. Robinson
Ann. Statist. 10(3): 915-925 (September, 1982). DOI: 10.1214/aos/1176345881


Some stationary and non-stationary time series arise from mixed distributions, the probabilities attached to the occurrence of certain values being positive, while a continuum of possible values is also involved. Such series are modeled in terms of a stationary Gaussian process $X_t$, which is censored when it crosses certain thresholds. Procedures are proposed for estimating the autocorrelation function of $X_t$. Their strong consistency and asymptotic normality are established. We suggest tests of the hypothesis that $X_t$ is white noise.


Download Citation

P. M. Robinson. "Analysis of Time Series from Mixed Distributions." Ann. Statist. 10 (3) 915 - 925, September, 1982.


Published: September, 1982
First available in Project Euclid: 12 April 2007

zbMATH: 0491.62078
MathSciNet: MR663442
Digital Object Identifier: 10.1214/aos/1176345881

Primary: 62M10
Secondary: 60G15 , 62M07

Keywords: central limit theorem , Gaussian process , Mixed distributions , moment estimator , nonlinear least squares , strong consistency , tests for white noise

Rights: Copyright © 1982 Institute of Mathematical Statistics

Vol.10 • No. 3 • September, 1982
Back to Top