Time Series Analysis and Multivariate Statistical Analysis.

reportActive / Technical Report | Accession Number: ADA161375 | Open PDF

Abstract:

The probability of an estimated moving average model being noninvertible was characterized. Generalizations of autocorrelation and partial autocorrelation coefficients are suggested for determining the orders of autoregressive moving average processes. Maximum likelihood estimators and likelihood ratio criteria were derived for a class of elliptically contoured distributions. Zonal polynomials were developed as characteristic vectors of a matrix of polynomials. Author

Author(s):
Anderson, Theodore W.
Author Organization(s):
STANFORD UNIV CA DEPT OF STATISTICS
Descriptive Note:
Final rept. 1 Jul 82-31 Jul 85,
Supplementary Note:
DOI: 10.21236/ADA161375
Pagination:
0007

Security Markings

DOCUMENT & CONTEXTUAL SUMMARY

Distribution:
Approved For Public Release

RECORD

Collection: TR
Identifying Numbers
Report Number(s):
ARO-19065.15-MA
Contract/Grant Number(s):
DAAG29-82-K-0156
Monitor Series:
19065.15-MA
 Subject Terms
Joint Capability Areas:
JCA_5_Command and Control; JCA_5.3_Planning; JCA_1_Force Support
Communities of Interest:
Materials and Manufacturing Processes
Descriptor(s):
*MULTIVARIATE ANALYSIS, *TIME SERIES ANALYSIS, MATHEMATICAL MODELS, DISTRIBUTION, MAXIMUM LIKELIHOOD ESTIMATION, AUTOCORRELATION, COEFFICIENTS, POLYNOMIALS, CONTOURS
Field(s)/Group(s):
Statistics and Probability
Keyword(s):
ARMA(Autoregressive Moving Average)
Report Date:
1985 Sep 01