Accession Number:

ADA076625

Title:

Maximum Likelihood Estimation for an Autoregressive Process WITH Missing Observations,

Descriptive Note:

Corporate Author:

PITTSBURGH UNIV PA DEPT OF MATHEMATICS AND STATISTICS

Personal Author(s):

Report Date:

1979-01-01

Pagination or Media Count:

12.0

Abstract:

Three methods are proposed for estimation of the parameters of an autoregressive process of order p with missing observations. These methods are based on the maximum likelihood approach and use the EM algorithm, the Newton-Raphson method and the method of scoring, which are applied to the likelihood equations. Finally, comparison on those methods is also discussed. Author

Subject Categories:

  • Statistics and Probability

Distribution Statement:

APPROVED FOR PUBLIC RELEASE