Power of edge exclusion tests in graphical gaussian models
Power of edge exclusion tests in graphical gaussian models
Asymptotic multivariate normal approximations to the joint distributions of edge exclusion test statistics for saturated graphical Gaussian models are derived. Non-signed and signed square-root versions of the likelihood ratio, Wald and score test statistics are considered. Non-central chi-squared approximations are also considered for the non-signed versions. These approximations are used to estimate the power of edge exclusion tests and an example is presented.
Southampton Statistical Sciences Research Institute, University of Southampton
Salguiero, Fatima
0b2ee646-4d9e-4a87-89c3-c01ddce33fe4
Smith, Peter
961a01a3-bf4c-43ca-9599-5be4fd5d3940
McDonald, John
9adae16e-e1e1-4ddf-bf4c-7231ee8c1c8e
2003
Salguiero, Fatima
0b2ee646-4d9e-4a87-89c3-c01ddce33fe4
Smith, Peter
961a01a3-bf4c-43ca-9599-5be4fd5d3940
McDonald, John
9adae16e-e1e1-4ddf-bf4c-7231ee8c1c8e
Salguiero, Fatima, Smith, Peter and McDonald, John
(2003)
Power of edge exclusion tests in graphical gaussian models
(S3RI Methodology Working Papers, M03/02)
Southampton, UK.
Southampton Statistical Sciences Research Institute, University of Southampton
21pp.
Record type:
Monograph
(Working Paper)
Abstract
Asymptotic multivariate normal approximations to the joint distributions of edge exclusion test statistics for saturated graphical Gaussian models are derived. Non-signed and signed square-root versions of the likelihood ratio, Wald and score test statistics are considered. Non-central chi-squared approximations are also considered for the non-signed versions. These approximations are used to estimate the power of edge exclusion tests and an example is presented.
More information
Published date: 2003
Identifiers
Local EPrints ID: 285
URI: http://eprints.soton.ac.uk/id/eprint/285
PURE UUID: 0a5bd54f-2b2a-45f2-b38a-b5bb4c0c0668
Catalogue record
Date deposited: 15 Jan 2004
Last modified: 16 Mar 2024 02:41
Export record
Contributors
Author:
Fatima Salguiero
Author:
John McDonald
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
