Open Access
2008 Optimising prediction error among completely monotone covariance sequences
Ross McVinish
Author Affiliations +
Electron. Commun. Probab. 13: 113-120 (2008). DOI: 10.1214/ECP.v13-1355


We provide a characterisation of Gaussian time series which optimise the one-step prediction error subject to the covariance sequence being completely monotone with the first $m$ covariances specified.


Download Citation

Ross McVinish. "Optimising prediction error among completely monotone covariance sequences." Electron. Commun. Probab. 13 113 - 120, 2008.


Accepted: 2 March 2008; Published: 2008
First available in Project Euclid: 6 June 2016

zbMATH: 1191.60049
MathSciNet: MR2386067
Digital Object Identifier: 10.1214/ECP.v13-1355

Primary: 60G25
Secondary: 44A60

Keywords: Aggregation , maximum entropy , moment space

Back to Top